From c9636244f86ae80b66e8ffb05ff755d85edf1988 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Wed, 6 Sep 2017 15:55:06 +0100
Subject: tools/testing/scatterlist: Test new __sg_alloc_table_from_pages

Exercise the new __sg_alloc_table_from_pages API (and through
it also the old sg_alloc_table_from_pages), checking that the
created table has the expected number of segments depending on
the sequence of input pages and other conditions.

v2: Move to data driven for readability.
v3: Add some more testcases and -fsanitize=undefined. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170906145506.14952-1-tvrtko.ursulin@linux.intel.com
[tursulin: whitespace fixup]
---
 tools/testing/scatterlist/Makefile   |  30 +++++++++
 tools/testing/scatterlist/linux/mm.h | 125 +++++++++++++++++++++++++++++++++++
 tools/testing/scatterlist/main.c     |  79 ++++++++++++++++++++++
 3 files changed, 234 insertions(+)
 create mode 100644 tools/testing/scatterlist/Makefile
 create mode 100644 tools/testing/scatterlist/linux/mm.h
 create mode 100644 tools/testing/scatterlist/main.c

(limited to 'tools')

diff --git a/tools/testing/scatterlist/Makefile b/tools/testing/scatterlist/Makefile
new file mode 100644
index 000000000000..933c3a6e4d77
--- /dev/null
+++ b/tools/testing/scatterlist/Makefile
@@ -0,0 +1,30 @@
+CFLAGS += -I. -I../../include -g -O2 -Wall -fsanitize=address
+LDFLAGS += -fsanitize=address -fsanitize=undefined
+TARGETS = main
+OFILES = main.o scatterlist.o
+
+ifeq ($(BUILD), 32)
+        CFLAGS += -m32
+        LDFLAGS += -m32
+endif
+
+targets: include $(TARGETS)
+
+main: $(OFILES)
+
+clean:
+	$(RM) $(TARGETS) $(OFILES) scatterlist.c linux/scatterlist.h linux/highmem.h linux/kmemleak.h asm/io.h
+	@rmdir asm
+
+scatterlist.c: ../../../lib/scatterlist.c
+	@sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
+
+.PHONY: include
+
+include: ../../../include/linux/scatterlist.h
+	@mkdir -p linux
+	@mkdir -p asm
+	@touch asm/io.h
+	@touch linux/highmem.h
+	@touch linux/kmemleak.h
+	@cp $< linux/scatterlist.h
diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h
new file mode 100644
index 000000000000..6f9ac14aa800
--- /dev/null
+++ b/tools/testing/scatterlist/linux/mm.h
@@ -0,0 +1,125 @@
+#ifndef _LINUX_MM_H
+#define _LINUX_MM_H
+
+#include <assert.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <limits.h>
+#include <stdio.h>
+
+typedef unsigned long dma_addr_t;
+
+#define unlikely
+
+#define BUG_ON(x) assert(!(x))
+
+#define WARN_ON(condition) ({                                           \
+	int __ret_warn_on = !!(condition);                              \
+	unlikely(__ret_warn_on);                                        \
+})
+
+#define WARN_ON_ONCE(condition) ({                              \
+	int __ret_warn_on = !!(condition);                      \
+	if (unlikely(__ret_warn_on))                            \
+		assert(0);                                      \
+	unlikely(__ret_warn_on);                                \
+})
+
+#define PAGE_SIZE	(4096)
+#define PAGE_SHIFT	(12)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+#define ALIGN(x, a)			__ALIGN_KERNEL((x), (a))
+
+#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+
+#define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
+
+#define virt_to_page(x)	((void *)x)
+#define page_address(x)	((void *)x)
+
+static inline unsigned long page_to_phys(struct page *page)
+{
+	assert(0);
+
+	return 0;
+}
+
+#define page_to_pfn(page) ((unsigned long)(page) / PAGE_SIZE)
+#define pfn_to_page(pfn) (void *)((pfn) * PAGE_SIZE)
+#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
+
+#define __min(t1, t2, min1, min2, x, y) ({              \
+	t1 min1 = (x);                                  \
+	t2 min2 = (y);                                  \
+	(void) (&min1 == &min2);                        \
+	min1 < min2 ? min1 : min2; })
+
+#define ___PASTE(a,b) a##b
+#define __PASTE(a,b) ___PASTE(a,b)
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#define min(x, y)                                       \
+	__min(typeof(x), typeof(y),                     \
+	      __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),   \
+	      x, y)
+
+#define min_t(type, x, y)                               \
+	__min(type, type,                               \
+	      __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),   \
+	      x, y)
+
+#define preemptible() (1)
+
+static inline void *kmap(struct page *page)
+{
+	assert(0);
+
+	return NULL;
+}
+
+static inline void *kmap_atomic(struct page *page)
+{
+	assert(0);
+
+	return NULL;
+}
+
+static inline void kunmap(void *addr)
+{
+	assert(0);
+}
+
+static inline void kunmap_atomic(void *addr)
+{
+	assert(0);
+}
+
+static inline unsigned long __get_free_page(unsigned int flags)
+{
+	return (unsigned long)malloc(PAGE_SIZE);
+}
+
+static inline void free_page(unsigned long page)
+{
+	free((void *)page);
+}
+
+static inline void *kmalloc(unsigned int size, unsigned int flags)
+{
+	return malloc(size);
+}
+
+#define kfree(x) free(x)
+
+#define kmemleak_alloc(a, b, c, d)
+#define kmemleak_free(a)
+
+#define PageSlab(p) (0)
+#define flush_kernel_dcache_page(p)
+
+#endif
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
new file mode 100644
index 000000000000..0a1464181226
--- /dev/null
+++ b/tools/testing/scatterlist/main.c
@@ -0,0 +1,79 @@
+#include <stdio.h>
+#include <assert.h>
+
+#include <linux/scatterlist.h>
+
+#define MAX_PAGES (64)
+
+static void set_pages(struct page **pages, const unsigned *array, unsigned num)
+{
+	unsigned int i;
+
+	assert(num < MAX_PAGES);
+	for (i = 0; i < num; i++)
+		pages[i] = (struct page *)(unsigned long)
+			   ((1 + array[i]) * PAGE_SIZE);
+}
+
+#define pfn(...) (unsigned []){ __VA_ARGS__ }
+
+int main(void)
+{
+	const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT;
+	struct test {
+		int alloc_ret;
+		unsigned num_pages;
+		unsigned *pfn;
+		unsigned size;
+		unsigned int max_seg;
+		unsigned int expected_segments;
+	} *test, tests[] = {
+		{ -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
+		{ -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 },
+		{ -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
+		{ 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 },
+		{ 0, 1, pfn(0), 1, sgmax, 1 },
+		{ 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 },
+		{ 0, 2, pfn(1, 0), 2 * PAGE_SIZE, sgmax, 2 },
+		{ 0, 3, pfn(0, 1, 2), 3 * PAGE_SIZE, sgmax, 1 },
+		{ 0, 3, pfn(0, 2, 1), 3 * PAGE_SIZE, sgmax, 3 },
+		{ 0, 3, pfn(0, 1, 3), 3 * PAGE_SIZE, sgmax, 2 },
+		{ 0, 3, pfn(1, 2, 4), 3 * PAGE_SIZE, sgmax, 2 },
+		{ 0, 3, pfn(1, 3, 4), 3 * PAGE_SIZE, sgmax, 2 },
+		{ 0, 4, pfn(0, 1, 3, 4), 4 * PAGE_SIZE, sgmax, 2 },
+		{ 0, 5, pfn(0, 1, 3, 4, 5), 5 * PAGE_SIZE, sgmax, 2 },
+		{ 0, 5, pfn(0, 1, 3, 4, 6), 5 * PAGE_SIZE, sgmax, 3 },
+		{ 0, 5, pfn(0, 1, 2, 3, 4), 5 * PAGE_SIZE, sgmax, 1 },
+		{ 0, 5, pfn(0, 1, 2, 3, 4), 5 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
+		{ 0, 6, pfn(0, 1, 2, 3, 4, 5), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
+		{ 0, 6, pfn(0, 2, 3, 4, 5, 6), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 4 },
+		{ 0, 6, pfn(0, 1, 3, 4, 5, 6), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
+		{ 0, 0, NULL, 0, 0, 0 },
+	};
+	unsigned int i;
+
+	for (i = 0, test = tests; test->expected_segments; test++, i++) {
+		struct page *pages[MAX_PAGES];
+		struct sg_table st;
+		int ret;
+
+		set_pages(pages, test->pfn, test->num_pages);
+
+		ret = __sg_alloc_table_from_pages(&st, pages, test->num_pages,
+						  0, test->size, test->max_seg,
+						  GFP_KERNEL);
+		assert(ret == test->alloc_ret);
+
+		if (test->alloc_ret)
+			continue;
+
+		assert(st.nents == test->expected_segments);
+		assert(st.orig_nents == test->expected_segments);
+
+		sg_free_table(&st);
+	}
+
+	assert(i == (sizeof(tests) / sizeof(tests[0])) - 1);
+
+	return 0;
+}
-- 
cgit v1.2.3


From bae30468dfc1522464f16051addd7bc7da6da75a Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Mon, 18 Sep 2017 15:30:56 -0400
Subject: bpf: Add uniqueness invariant to trivial lpm test implementation

The 'trivial' lpm implementation in this test allows equivalent nodes
to be added (that is, nodes consisting of the same prefix and prefix
length).  For lookup operations, this is fine because insertion happens
at the head of the (singly linked) list and the first, best match is
returned.  In order to support deletion, the tlpm data structue must
first enforce uniqueness.  This change modifies the insertion algorithm
to search for equivalent nodes and remove them.  Note: the
BPF_MAP_TYPE_LPM_TRIE already has a uniqueness invariant that is
implemented as node replacement.

Signed-off-by: Craig Gallek <kraig@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_lpm_map.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index e97565243d59..a5ed7c4f1819 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -31,6 +31,10 @@ struct tlpm_node {
 	uint8_t key[];
 };
 
+static struct tlpm_node *tlpm_match(struct tlpm_node *list,
+				    const uint8_t *key,
+				    size_t n_bits);
+
 static struct tlpm_node *tlpm_add(struct tlpm_node *list,
 				  const uint8_t *key,
 				  size_t n_bits)
@@ -38,9 +42,17 @@ static struct tlpm_node *tlpm_add(struct tlpm_node *list,
 	struct tlpm_node *node;
 	size_t n;
 
+	n = (n_bits + 7) / 8;
+
+	/* 'overwrite' an equivalent entry if one already exists */
+	node = tlpm_match(list, key, n_bits);
+	if (node && node->n_bits == n_bits) {
+		memcpy(node->key, key, n);
+		return list;
+	}
+
 	/* add new entry with @key/@n_bits to @list and return new head */
 
-	n = (n_bits + 7) / 8;
 	node = malloc(sizeof(*node) + n);
 	assert(node);
 
-- 
cgit v1.2.3


From e8d1749910b56a7248cb9a5392274348d10108bb Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Mon, 18 Sep 2017 15:30:57 -0400
Subject: bpf: Test deletion in BPF_MAP_TYPE_LPM_TRIE

Extend the 'random' operation tests to include a delete operation
(delete half of the nodes from both lpm implementions and ensure
that lookups are still equivalent).

Also, add a simple IPv4 test which verifies lookup behavior as nodes
are deleted from the tree.

Signed-off-by: Craig Gallek <kraig@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_lpm_map.c | 187 ++++++++++++++++++++++++++++-
 1 file changed, 183 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index a5ed7c4f1819..6fedb9fec36b 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -104,6 +104,34 @@ static struct tlpm_node *tlpm_match(struct tlpm_node *list,
 	return best;
 }
 
+static struct tlpm_node *tlpm_delete(struct tlpm_node *list,
+				     const uint8_t *key,
+				     size_t n_bits)
+{
+	struct tlpm_node *best = tlpm_match(list, key, n_bits);
+	struct tlpm_node *node;
+
+	if (!best || best->n_bits != n_bits)
+		return list;
+
+	if (best == list) {
+		node = best->next;
+		free(best);
+		return node;
+	}
+
+	for (node = list; node; node = node->next) {
+		if (node->next == best) {
+			node->next = best->next;
+			free(best);
+			return list;
+		}
+	}
+	/* should never get here */
+	assert(0);
+	return list;
+}
+
 static void test_lpm_basic(void)
 {
 	struct tlpm_node *list = NULL, *t1, *t2;
@@ -126,6 +154,13 @@ static void test_lpm_basic(void)
 	assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15));
 	assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16));
 
+	list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16);
+	assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+	assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
+
+	list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8);
+	assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+
 	tlpm_clear(list);
 }
 
@@ -170,7 +205,7 @@ static void test_lpm_order(void)
 
 static void test_lpm_map(int keysize)
 {
-	size_t i, j, n_matches, n_nodes, n_lookups;
+	size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
 	struct tlpm_node *t, *list = NULL;
 	struct bpf_lpm_trie_key *key;
 	uint8_t *data, *value;
@@ -182,6 +217,7 @@ static void test_lpm_map(int keysize)
 	 */
 
 	n_matches = 0;
+	n_matches_after_delete = 0;
 	n_nodes = 1 << 8;
 	n_lookups = 1 << 16;
 
@@ -235,15 +271,54 @@ static void test_lpm_map(int keysize)
 		}
 	}
 
+	/* Remove the first half of the elements in the tlpm and the
+	 * corresponding nodes from the bpf-lpm.  Then run the same
+	 * large number of random lookups in both and make sure they match.
+	 * Note: we need to count the number of nodes actually inserted
+	 * since there may have been duplicates.
+	 */
+	for (i = 0, t = list; t; i++, t = t->next)
+		;
+	for (j = 0; j < i / 2; ++j) {
+		key->prefixlen = list->n_bits;
+		memcpy(key->data, list->key, keysize);
+		r = bpf_map_delete_elem(map, key);
+		assert(!r);
+		list = tlpm_delete(list, list->key, list->n_bits);
+		assert(list);
+	}
+	for (i = 0; i < n_lookups; ++i) {
+		for (j = 0; j < keysize; ++j)
+			data[j] = rand() & 0xff;
+
+		t = tlpm_match(list, data, 8 * keysize);
+
+		key->prefixlen = 8 * keysize;
+		memcpy(key->data, data, keysize);
+		r = bpf_map_lookup_elem(map, key, value);
+		assert(!r || errno == ENOENT);
+		assert(!t == !!r);
+
+		if (t) {
+			++n_matches_after_delete;
+			assert(t->n_bits == value[keysize]);
+			for (j = 0; j < t->n_bits; ++j)
+				assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
+				       (value[j / 8] & (1 << (7 - j % 8))));
+		}
+	}
+
 	close(map);
 	tlpm_clear(list);
 
 	/* With 255 random nodes in the map, we are pretty likely to match
 	 * something on every lookup. For statistics, use this:
 	 *
-	 *     printf("  nodes: %zu\n"
-	 *            "lookups: %zu\n"
-	 *            "matches: %zu\n", n_nodes, n_lookups, n_matches);
+	 *     printf("          nodes: %zu\n"
+	 *            "        lookups: %zu\n"
+	 *            "        matches: %zu\n"
+	 *            "matches(delete): %zu\n",
+	 *            n_nodes, n_lookups, n_matches, n_matches_after_delete);
 	 */
 }
 
@@ -343,6 +418,108 @@ static void test_lpm_ipaddr(void)
 	close(map_fd_ipv6);
 }
 
+static void test_lpm_delete(void)
+{
+	struct bpf_lpm_trie_key *key;
+	size_t key_size;
+	int map_fd;
+	__u64 value;
+
+	key_size = sizeof(*key) + sizeof(__u32);
+	key = alloca(key_size);
+
+	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+				key_size, sizeof(value),
+				100, BPF_F_NO_PREALLOC);
+	assert(map_fd >= 0);
+
+	/* Add nodes:
+	 * 192.168.0.0/16   (1)
+	 * 192.168.0.0/24   (2)
+	 * 192.168.128.0/24 (3)
+	 * 192.168.1.0/24   (4)
+	 *
+	 *         (1)
+	 *        /   \
+         *     (IM)    (3)
+	 *    /   \
+         *   (2)  (4)
+	 */
+	value = 1;
+	key->prefixlen = 16;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	value = 2;
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	value = 3;
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.128.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	value = 4;
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.1.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	/* remove non-existent node */
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "10.0.0.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
+		errno == ENOENT);
+
+	/* assert initial lookup */
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.0.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 2);
+
+	/* remove leaf node */
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.0.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 1);
+
+	/* remove leaf (and intermediary) node */
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.1.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.1.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 1);
+
+	/* remove root node */
+	key->prefixlen = 16;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.128.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 3);
+
+	/* remove last node */
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.128.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.128.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
+		errno == ENOENT);
+
+	close(map_fd);
+}
+
 int main(void)
 {
 	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
@@ -365,6 +542,8 @@ int main(void)
 
 	test_lpm_ipaddr();
 
+	test_lpm_delete();
+
 	printf("test_lpm: OK\n");
 	return 0;
 }
-- 
cgit v1.2.3


From 69e33b2754ea4fbe4fdd2d18bc8ca05d8670a5c2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 19 Sep 2017 14:42:17 +0200
Subject: selftests: rtnetlink.sh: add test case for device ifalias

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 57 ++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 57b5ff576240..4b48de565cae 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -15,6 +15,14 @@ check_err()
 	fi
 }
 
+# same but inverted -- used when command must fail for test to pass
+check_fail()
+{
+	if [ $1 -eq 0 ]; then
+		ret=1
+	fi
+}
+
 kci_add_dummy()
 {
 	ip link add name "$devdummy" type dummy
@@ -235,6 +243,54 @@ kci_test_addrlabel()
 	echo "PASS: ipv6 addrlabel"
 }
 
+kci_test_ifalias()
+{
+	ret=0
+	namewant=$(uuidgen)
+	syspathname="/sys/class/net/$devdummy/ifalias"
+
+	ip link set dev "$devdummy" alias "$namewant"
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: cannot set interface alias of $devdummy to $namewant"
+		return 1
+	fi
+
+	ip link show "$devdummy" | grep -q "alias $namewant"
+	check_err $?
+
+	if [ -r "$syspathname" ] ; then
+		read namehave < "$syspathname"
+		if [ "$namewant" != "$namehave" ]; then
+			echo "FAIL: did set ifalias $namewant but got $namehave"
+			return 1
+		fi
+
+		namewant=$(uuidgen)
+		echo "$namewant" > "$syspathname"
+	        ip link show "$devdummy" | grep -q "alias $namewant"
+		check_err $?
+
+		# sysfs interface allows to delete alias again
+		echo "" > "$syspathname"
+
+	        ip link show "$devdummy" | grep -q "alias $namewant"
+		check_fail $?
+
+		# re-add the alias -- kernel should free mem when dummy dev is removed
+		ip link set dev "$devdummy" alias "$namewant"
+		check_err $?
+	fi
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: set interface alias $devdummy to $namewant"
+		return 1
+	fi
+
+	echo "PASS: set ifalias $namewant for $devdummy"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -249,6 +305,7 @@ kci_test_rtnl()
 	kci_test_gre
 	kci_test_bridge
 	kci_test_addrlabel
+	kci_test_ifalias
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From b655fc1c2ee1c2b2d07c0b6f432798b91202718c Mon Sep 17 00:00:00 2001
From: Joel Fernandes <joelaf@google.com>
Date: Wed, 20 Sep 2017 09:11:58 -0700
Subject: samples/bpf: Fix pt_regs issues when cross-compiling

BPF samples fail to build when cross-compiling for ARM64 because of incorrect
pt_regs param selection. This is because clang defines __x86_64__ and
bpf_headers thinks we're building for x86. Since clang is building for the BPF
target, it shouldn't make assumptions about what target the BPF program is
going to run on. To fix this, lets pass ARCH so the header knows which target
the BPF program is being compiled for and can use the correct pt_regs code.

Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Joel Fernandes <joelaf@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/Makefile                      |  2 +-
 tools/testing/selftests/bpf/bpf_helpers.h | 56 +++++++++++++++++++++++++++----
 2 files changed, 50 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 13f74b67ca44..ebc2ad69b62c 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -230,7 +230,7 @@ $(obj)/%.o: $(src)/%.c
 	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
 		-I$(srctree)/tools/testing/selftests/bpf/ \
 		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
-		-Wno-compare-distinct-pointer-types \
+		-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
 		-Wno-unknown-warning-option \
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 36fb9161b34a..4875395b0b52 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -109,7 +109,47 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
 static int (*bpf_skb_change_head)(void *, int len, int flags) =
 	(void *) BPF_FUNC_skb_change_head;
 
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+	#define bpf_target_x86
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_s930x)
+	#define bpf_target_s930x
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+	#define bpf_target_arm64
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_mips)
+	#define bpf_target_mips
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+	#define bpf_target_powerpc
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+	#define bpf_target_sparc
+	#define bpf_target_defined
+#else
+	#undef bpf_target_defined
+#endif
+
+/* Fall back to what the compiler says */
+#ifndef bpf_target_defined
 #if defined(__x86_64__)
+	#define bpf_target_x86
+#elif defined(__s390x__)
+	#define bpf_target_s930x
+#elif defined(__aarch64__)
+	#define bpf_target_arm64
+#elif defined(__mips__)
+	#define bpf_target_mips
+#elif defined(__powerpc__)
+	#define bpf_target_powerpc
+#elif defined(__sparc__)
+	#define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
 
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
@@ -122,7 +162,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
 
-#elif defined(__s390x__)
+#elif defined(bpf_target_s390x)
 
 #define PT_REGS_PARM1(x) ((x)->gprs[2])
 #define PT_REGS_PARM2(x) ((x)->gprs[3])
@@ -135,7 +175,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->gprs[15])
 #define PT_REGS_IP(x) ((x)->psw.addr)
 
-#elif defined(__aarch64__)
+#elif defined(bpf_target_arm64)
 
 #define PT_REGS_PARM1(x) ((x)->regs[0])
 #define PT_REGS_PARM2(x) ((x)->regs[1])
@@ -148,7 +188,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->pc)
 
-#elif defined(__mips__)
+#elif defined(bpf_target_mips)
 
 #define PT_REGS_PARM1(x) ((x)->regs[4])
 #define PT_REGS_PARM2(x) ((x)->regs[5])
@@ -161,7 +201,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->regs[29])
 #define PT_REGS_IP(x) ((x)->cp0_epc)
 
-#elif defined(__powerpc__)
+#elif defined(bpf_target_powerpc)
 
 #define PT_REGS_PARM1(x) ((x)->gpr[3])
 #define PT_REGS_PARM2(x) ((x)->gpr[4])
@@ -172,7 +212,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
-#elif defined(__sparc__)
+#elif defined(bpf_target_sparc)
 
 #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
@@ -182,6 +222,8 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
 #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+
+/* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
 #define PT_REGS_IP(x) ((x)->tpc)
 #else
@@ -190,10 +232,10 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 
 #endif
 
-#ifdef __powerpc__
+#ifdef bpf_target_powerpc
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(__sparc__)
+#elif bpf_target_sparc
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 #else
-- 
cgit v1.2.3


From ac29991ba137cc0e3b0f647fb41e79300230f15c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 25 Sep 2017 02:25:52 +0200
Subject: bpf: update bpf.h uapi header for tools

Looks like a couple of updates missed to get carried into tools/include/uapi/,
so copy the bpf.h header as usual to pull in latest updates.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/include/uapi/linux/bpf.h | 45 ++++++++++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 461811e57140..e43491ac4823 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -143,12 +143,6 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-enum bpf_sockmap_flags {
-	BPF_SOCKMAP_UNSPEC,
-	BPF_SOCKMAP_STRPARSER,
-	__MAX_BPF_SOCKMAP_FLAG
-};
-
 /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
  * to the given target_fd cgroup the descendent cgroup will be able to
  * override effective bpf program that was inherited from this cgroup
@@ -368,9 +362,20 @@ union bpf_attr {
  * int bpf_redirect(ifindex, flags)
  *     redirect to another netdev
  *     @ifindex: ifindex of the net device
- *     @flags: bit 0 - if set, redirect to ingress instead of egress
- *             other bits - reserved
- *     Return: TC_ACT_REDIRECT
+ *     @flags:
+ *	  cls_bpf:
+ *          bit 0 - if set, redirect to ingress instead of egress
+ *          other bits - reserved
+ *	  xdp_bpf:
+ *	    all bits - reserved
+ *     Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
+ *	       xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
+ * int bpf_redirect_map(map, key, flags)
+ *     redirect to endpoint in map
+ *     @map: pointer to dev map
+ *     @key: index in map to lookup
+ *     @flags: --
+ *     Return: XDP_REDIRECT on success or XDP_ABORT on error
  *
  * u32 bpf_get_route_realm(skb)
  *     retrieve a dst's tclassid
@@ -577,6 +582,12 @@ union bpf_attr {
  *	@map: pointer to sockmap to update
  *	@key: key to insert/update sock in map
  *	@flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ *     Adjust the xdp_md.data_meta by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data_meta
+ *     Return: 0 on success or negative on error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -632,7 +643,8 @@ union bpf_attr {
 	FN(skb_adjust_room),		\
 	FN(redirect_map),		\
 	FN(sk_redirect_map),		\
-	FN(sock_map_update),
+	FN(sock_map_update),		\
+	FN(xdp_adjust_meta),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -710,7 +722,7 @@ struct __sk_buff {
 	__u32 data_end;
 	__u32 napi_id;
 
-	/* accessed by BPF_PROG_TYPE_sk_skb types */
+	/* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
 	__u32 local_ip4;	/* Stored in network byte order */
@@ -718,6 +730,9 @@ struct __sk_buff {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	/* ... here. */
+
+	__u32 data_meta;
 };
 
 struct bpf_tunnel_key {
@@ -753,20 +768,23 @@ struct bpf_sock {
 	__u32 family;
 	__u32 type;
 	__u32 protocol;
+	__u32 mark;
+	__u32 priority;
 };
 
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
- * return codes are reserved for future use. Unknown return codes will result
- * in packet drop.
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
  */
 enum xdp_action {
 	XDP_ABORTED = 0,
 	XDP_DROP,
 	XDP_PASS,
 	XDP_TX,
+	XDP_REDIRECT,
 };
 
 /* user accessible metadata for XDP packet hook
@@ -775,6 +793,7 @@ enum xdp_action {
 struct xdp_md {
 	__u32 data;
 	__u32 data_end;
+	__u32 data_meta;
 };
 
 enum sk_action {
-- 
cgit v1.2.3


From 22c8852624fc90a90709d1237625ca57999c5092 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 25 Sep 2017 02:25:53 +0200
Subject: bpf: improve selftests and add tests for meta pointer

Add various test_verifier selftests, and a simple xdp/tc functional
test that is being attached to veths. Also let new versions of clang
use the recently added -mcpu=probe support [1] for the BPF target,
so that it can probe the underlying kernel for BPF insn set extensions.
We could also just set this options always, where older versions just
ignore it and give a note to the user that the -mcpu value is not
supported, but given emitting the note cannot be turned off from clang
side lets not confuse users running selftests with it, thus fallback
to the default generic one when we see that clang doesn't support it.
Also allow CPU option to be overridden in the Makefile from command
line.

  [1] https://github.com/llvm-mirror/llvm/commit/d7276a40d87b89aed89978dec6457a5b8b3a0db5

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/Makefile         |  21 ++-
 tools/testing/selftests/bpf/bpf_helpers.h    |   2 +
 tools/testing/selftests/bpf/test_verifier.c  | 247 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_xdp_meta.c  |  53 ++++++
 tools/testing/selftests/bpf/test_xdp_meta.sh |  51 ++++++
 5 files changed, 370 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/test_xdp_meta.c
 create mode 100755 tools/testing/selftests/bpf/test_xdp_meta.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f4b23d697448..924af8d79bde 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -15,9 +15,10 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
-	test_pkt_md_access.o test_xdp_redirect.o sockmap_parse_prog.o sockmap_verdict_prog.o
+	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
+	sockmap_verdict_prog.o
 
-TEST_PROGS := test_kmod.sh test_xdp_redirect.sh
+TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
 
 include ../lib.mk
 
@@ -34,8 +35,20 @@ $(BPFOBJ): force
 	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
 CLANG ?= clang
+LLC   ?= llc
+
+PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+
+# Let newer LLVM versions transparently probe the kernel for availability
+# of full BPF instruction set.
+ifeq ($(PROBE),)
+  CPU ?= probe
+else
+  CPU ?= generic
+endif
 
 %.o: %.c
 	$(CLANG) -I. -I./include/uapi -I../../../include/uapi \
-		-Wno-compare-distinct-pointer-types \
-		-O2 -target bpf -c $< -o $@
+		 -Wno-compare-distinct-pointer-types          \
+		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	$(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 4875395b0b52..a56053db26f5 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -62,6 +62,8 @@ static unsigned long long (*bpf_get_prandom_u32)(void) =
 	(void *) BPF_FUNC_get_prandom_u32;
 static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 	(void *) BPF_FUNC_xdp_adjust_head;
+static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
+	(void *) BPF_FUNC_xdp_adjust_meta;
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 26f3250bdcd2..a0426147523d 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6645,6 +6645,253 @@ static struct bpf_test tests[] = {
 		.errstr = "BPF_END uses reserved fields",
 		.result = REJECT,
 	},
+	{
+		"meta access, test1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 8),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet, off=-8",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test3",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test4",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test5",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_4, 3),
+			BPF_MOV64_IMM(BPF_REG_2, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_xdp_adjust_meta),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "R3 !read_ok",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test6",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test7",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test8",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test9",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test10",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_IMM(BPF_REG_5, 42),
+			BPF_MOV64_IMM(BPF_REG_6, 24),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_5, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test11",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_IMM(BPF_REG_5, 42),
+			BPF_MOV64_IMM(BPF_REG_6, 24),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_5, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test12",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 5),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c
new file mode 100644
index 000000000000..8d0182650653
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_meta.c
@@ -0,0 +1,53 @@
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
+
+#include "bpf_helpers.h"
+
+#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
+#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
+#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
+
+SEC("t")
+int ing_cls(struct __sk_buff *ctx)
+{
+	__u8 *data, *data_meta, *data_end;
+	__u32 diff = 0;
+
+	data_meta = ctx_ptr(ctx, data_meta);
+	data_end  = ctx_ptr(ctx, data_end);
+	data      = ctx_ptr(ctx, data);
+
+	if (data + ETH_ALEN > data_end ||
+	    data_meta + round_up(ETH_ALEN, 4) > data)
+		return TC_ACT_SHOT;
+
+	diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0];
+	diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2];
+
+	return diff ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+SEC("x")
+int ing_xdp(struct xdp_md *ctx)
+{
+	__u8 *data, *data_meta, *data_end;
+	int ret;
+
+	ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4));
+	if (ret < 0)
+		return XDP_DROP;
+
+	data_meta = ctx_ptr(ctx, data_meta);
+	data_end  = ctx_ptr(ctx, data_end);
+	data      = ctx_ptr(ctx, data);
+
+	if (data + ETH_ALEN > data_end ||
+	    data_meta + round_up(ETH_ALEN, 4) > data)
+		return XDP_DROP;
+
+	__builtin_memcpy(data_meta, data, ETH_ALEN);
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh
new file mode 100755
index 000000000000..307aa856cee3
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_meta.sh
@@ -0,0 +1,51 @@
+#!/bin/sh
+
+cleanup()
+{
+	if [ "$?" = "0" ]; then
+		echo "selftests: test_xdp_meta [PASS]";
+	else
+		echo "selftests: test_xdp_meta [FAILED]";
+	fi
+
+	set +e
+	ip netns del ns1 2> /dev/null
+	ip netns del ns2 2> /dev/null
+}
+
+ip link set dev lo xdp off 2>/dev/null > /dev/null
+if [ $? -ne 0 ];then
+	echo "selftests: [SKIP] Could not run test without the ip xdp support"
+	exit 0
+fi
+set -e
+
+ip netns add ns1
+ip netns add ns2
+
+trap cleanup 0 2 3 6 9
+
+ip link add veth1 type veth peer name veth2
+
+ip link set veth1 netns ns1
+ip link set veth2 netns ns2
+
+ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1
+ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2
+
+ip netns exec ns1 tc qdisc add dev veth1 clsact
+ip netns exec ns2 tc qdisc add dev veth2 clsact
+
+ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t
+ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t
+
+ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x
+ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x
+
+ip netns exec ns1 ip link set dev veth1 up
+ip netns exec ns2 ip link set dev veth2 up
+
+ip netns exec ns1 ping -c 1 10.1.1.22
+ip netns exec ns2 ping -c 1 10.1.1.11
+
+exit 0
-- 
cgit v1.2.3


From a586cb4937fa328a857c8d7fbefb986d347bd4a7 Mon Sep 17 00:00:00 2001
From: Yasunori Goto <y-goto@jp.fujitsu.com>
Date: Fri, 22 Sep 2017 16:46:26 +0900
Subject: nfit_test Make private definitions to command emulation

Move private definitions to command emulation.
These definitions were originally defined at include/uapi/linux/ndctl.h,
but they are used at only nfit_test emulation now.

Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit_test.h | 47 +++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index d3d63dd5ed38..52c83be9dcfa 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -32,6 +32,53 @@ struct nfit_test_resource {
 	void *buf;
 };
 
+#define ND_TRANSLATE_SPA_STATUS_INVALID_SPA  2
+
+/* nfit commands */
+enum nfit_cmd_num {
+	NFIT_CMD_TRANSLATE_SPA = 5,
+	NFIT_CMD_ARS_INJECT_SET = 7,
+	NFIT_CMD_ARS_INJECT_CLEAR = 8,
+	NFIT_CMD_ARS_INJECT_GET = 9,
+};
+
+struct nd_cmd_translate_spa {
+	__u64 spa;
+	__u32 status;
+	__u8  flags;
+	__u8  _reserved[3];
+	__u64 translate_length;
+	__u32 num_nvdimms;
+	struct nd_nvdimm_device {
+		__u32 nfit_device_handle;
+		__u32 _reserved;
+		__u64 dpa;
+	} __packed devices[0];
+
+} __packed;
+
+struct nd_cmd_ars_err_inj {
+	__u64 err_inj_spa_range_base;
+	__u64 err_inj_spa_range_length;
+	__u8  err_inj_options;
+	__u32 status;
+} __packed;
+
+struct nd_cmd_ars_err_inj_clr {
+	__u64 err_inj_clr_spa_range_base;
+	__u64 err_inj_clr_spa_range_length;
+	__u32 status;
+} __packed;
+
+struct nd_cmd_ars_err_inj_stat {
+	__u32 status;
+	__u32 inj_err_rec_count;
+	struct nd_error_stat_query_record {
+		__u64 err_inj_stat_spa_range_base;
+		__u64 err_inj_stat_spa_range_length;
+	} __packed record[0];
+} __packed;
+
 union acpi_object;
 typedef void *acpi_handle;
 
-- 
cgit v1.2.3


From 61f26d92510ea1e30f9b69097b34b6a522daa1d2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 26 Sep 2017 07:40:42 +0200
Subject: selftests: rtnetlink.sh: add rudimentary vrf test

Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 42 ++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 4b48de565cae..a048f7a5f94c 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -291,6 +291,47 @@ kci_test_ifalias()
 	echo "PASS: set ifalias $namewant for $devdummy"
 }
 
+kci_test_vrf()
+{
+	vrfname="test-vrf"
+	ret=0
+
+	ip link show type vrf 2>/dev/null
+	if [ $? -ne 0 ]; then
+		echo "SKIP: vrf: iproute2 too old"
+		return 0
+	fi
+
+	ip link add "$vrfname" type vrf table 10
+	check_err $?
+	if [ $ret -ne 0 ];then
+		echo "FAIL: can't add vrf interface, skipping test"
+		return 0
+	fi
+
+	ip -br link show type vrf | grep -q "$vrfname"
+	check_err $?
+	if [ $ret -ne 0 ];then
+		echo "FAIL: created vrf device not found"
+		return 1
+	fi
+
+	ip link set dev "$vrfname" up
+	check_err $?
+
+	ip link set dev "$devdummy" master "$vrfname"
+	check_err $?
+	ip link del dev "$vrfname"
+	check_err $?
+
+	if [ $ret -ne 0 ];then
+		echo "FAIL: vrf"
+		return 1
+	fi
+
+	echo "PASS: vrf"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -306,6 +347,7 @@ kci_test_rtnl()
 	kci_test_bridge
 	kci_test_addrlabel
 	kci_test_ifalias
+	kci_test_vrf
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From 88cda1c9da02c8aa31e1d5dcf22e8a35cc8c19f2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 27 Sep 2017 14:37:54 -0700
Subject: bpf: libbpf: Provide basic API support to specify BPF obj name

This patch extends the libbpf to provide API support to
allow specifying BPF object name.

In tools/lib/bpf/libbpf, the C symbol of the function
and the map is used.  Regarding section name, all maps are
under the same section named "maps".  Hence, section name
is not a good choice for map's name.  To be consistent with
map, bpf_prog also follows and uses its function symbol as
the prog's name.

This patch adds logic to collect function's symbols in libbpf.
There is existing codes to collect the map's symbols and no change
is needed.

The bpf_load_program_name() and bpf_map_create_name() are
added to take the name argument.  For the other bpf_map_create_xxx()
variants, a name argument is directly added to them.

In samples/bpf, bpf_load.c in particular, the symbol is also
used as the map's name and the map symbols has already been
collected in the existing code.  For bpf_prog, bpf_load.c does
not collect the function symbol name.  We can consider to collect
them later if there is a need to continue supporting the bpf_load.c.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/bpf_load.c                      |   2 +
 samples/bpf/map_perf_test_user.c            |   1 +
 tools/include/uapi/linux/bpf.h              |  10 +++
 tools/lib/bpf/bpf.c                         |  57 +++++++++++----
 tools/lib/bpf/bpf.h                         |  23 ++++--
 tools/lib/bpf/libbpf.c                      | 109 +++++++++++++++++++++-------
 tools/testing/selftests/bpf/test_verifier.c |   2 +-
 7 files changed, 157 insertions(+), 47 deletions(-)

(limited to 'tools')

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 6aa50098dfb8..18b1c8dd0391 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -221,6 +221,7 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps,
 			int inner_map_fd = map_fd[maps[i].def.inner_map_idx];
 
 			map_fd[i] = bpf_create_map_in_map_node(maps[i].def.type,
+							maps[i].name,
 							maps[i].def.key_size,
 							inner_map_fd,
 							maps[i].def.max_entries,
@@ -228,6 +229,7 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps,
 							numa_node);
 		} else {
 			map_fd[i] = bpf_create_map_node(maps[i].def.type,
+							maps[i].name,
 							maps[i].def.key_size,
 							maps[i].def.value_size,
 							maps[i].def.max_entries,
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index a0310fc70057..519d9af4b04a 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -137,6 +137,7 @@ static void do_test_lru(enum test_type test, int cpu)
 
 			inner_lru_map_fds[cpu] =
 				bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH,
+						    test_map_names[INNER_LRU_HASH_PREALLOC],
 						    sizeof(uint32_t),
 						    sizeof(long),
 						    inner_lru_hash_size, 0,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e43491ac4823..6d2137b4cf38 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -175,6 +175,8 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
+#define BPF_OBJ_NAME_LEN 16U
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -188,6 +190,7 @@ union bpf_attr {
 		__u32	numa_node;	/* numa node (effective only if
 					 * BPF_F_NUMA_NODE is set).
 					 */
+		__u8	map_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -210,6 +213,7 @@ union bpf_attr {
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
+		__u8		prog_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -812,6 +816,11 @@ struct bpf_prog_info {
 	__u32 xlated_prog_len;
 	__aligned_u64 jited_prog_insns;
 	__aligned_u64 xlated_prog_insns;
+	__u64 load_time;	/* ns since boottime */
+	__u32 created_by_uid;
+	__u32 nr_map_ids;
+	__aligned_u64 map_ids;
+	__u8  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -821,6 +830,7 @@ struct bpf_map_info {
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 map_flags;
+	__u8  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1d6907d379c9..daf624e4c720 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -46,6 +46,8 @@
 # endif
 #endif
 
+#define min(x, y) ((x) < (y) ? (x) : (y))
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -57,10 +59,11 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 	return syscall(__NR_bpf, cmd, attr, size);
 }
 
-int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
-			int value_size, int max_entries, __u32 map_flags,
-			int node)
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags, int node)
 {
+	__u32 name_len = name ? strlen(name) : 0;
 	union bpf_attr attr;
 
 	memset(&attr, '\0', sizeof(attr));
@@ -70,6 +73,8 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
 	attr.map_flags = map_flags;
+	memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+
 	if (node >= 0) {
 		attr.map_flags |= BPF_F_NUMA_NODE;
 		attr.numa_node = node;
@@ -81,14 +86,23 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
 int bpf_create_map(enum bpf_map_type map_type, int key_size,
 		   int value_size, int max_entries, __u32 map_flags)
 {
-	return bpf_create_map_node(map_type, key_size, value_size,
+	return bpf_create_map_node(map_type, NULL, key_size, value_size,
 				   max_entries, map_flags, -1);
 }
 
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
-			       int inner_map_fd, int max_entries,
+int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags)
+{
+	return bpf_create_map_node(map_type, name, key_size, value_size,
+				   max_entries, map_flags, -1);
+}
+
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
+			       int key_size, int inner_map_fd, int max_entries,
 			       __u32 map_flags, int node)
 {
+	__u32 name_len = name ? strlen(name) : 0;
 	union bpf_attr attr;
 
 	memset(&attr, '\0', sizeof(attr));
@@ -99,6 +113,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
 	attr.inner_map_fd = inner_map_fd;
 	attr.max_entries = max_entries;
 	attr.map_flags = map_flags;
+	memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+
 	if (node >= 0) {
 		attr.map_flags |= BPF_F_NUMA_NODE;
 		attr.numa_node = node;
@@ -107,19 +123,24 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
-			  int inner_map_fd, int max_entries, __u32 map_flags)
+int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
+			  int key_size, int inner_map_fd, int max_entries,
+			  __u32 map_flags)
 {
-	return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd,
-					  max_entries, map_flags, -1);
+	return bpf_create_map_in_map_node(map_type, name, key_size,
+					  inner_map_fd, max_entries, map_flags,
+					  -1);
 }
 
-int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		     size_t insns_cnt, const char *license,
-		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
+int bpf_load_program_name(enum bpf_prog_type type, const char *name,
+			  const struct bpf_insn *insns,
+			  size_t insns_cnt, const char *license,
+			  __u32 kern_version, char *log_buf,
+			  size_t log_buf_sz)
 {
 	int fd;
 	union bpf_attr attr;
+	__u32 name_len = name ? strlen(name) : 0;
 
 	bzero(&attr, sizeof(attr));
 	attr.prog_type = type;
@@ -130,6 +151,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	attr.log_size = 0;
 	attr.log_level = 0;
 	attr.kern_version = kern_version;
+	memcpy(attr.prog_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
 
 	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 	if (fd >= 0 || !log_buf || !log_buf_sz)
@@ -143,6 +165,15 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
 
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		     size_t insns_cnt, const char *license,
+		     __u32 kern_version, char *log_buf,
+		     size_t log_buf_sz)
+{
+	return bpf_load_program_name(type, NULL, insns, insns_cnt, license,
+				     kern_version, log_buf, log_buf_sz);
+}
+
 int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		       size_t insns_cnt, int strict_alignment,
 		       const char *license, __u32 kern_version,
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index b8ea5843c39e..118d00535a0d 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,19 +24,28 @@
 #include <linux/bpf.h>
 #include <stddef.h>
 
-int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
-			int value_size, int max_entries, __u32 map_flags,
-			int node);
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags, int node);
+int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags);
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, __u32 map_flags);
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
-			       int inner_map_fd, int max_entries,
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
+			       int key_size, int inner_map_fd, int max_entries,
 			       __u32 map_flags, int node);
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
-			  int inner_map_fd, int max_entries, __u32 map_flags);
+int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
+			  int key_size, int inner_map_fd, int max_entries,
+			  __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
+int bpf_load_program_name(enum bpf_prog_type type, const char *name,
+			  const struct bpf_insn *insns,
+			  size_t insns_cnt, const char *license,
+			  __u32 kern_version, char *log_buf,
+			  size_t log_buf_sz);
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		     size_t insns_cnt, const char *license,
 		     __u32 kern_version, char *log_buf,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 35f6dfcdc565..4f402dcdf372 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -171,6 +171,7 @@ int libbpf_strerror(int err, char *buf, size_t size)
 struct bpf_program {
 	/* Index in elf obj file, for relocation use. */
 	int idx;
+	char *name;
 	char *section_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt;
@@ -283,6 +284,7 @@ static void bpf_program__exit(struct bpf_program *prog)
 	prog->clear_priv = NULL;
 
 	bpf_program__unload(prog);
+	zfree(&prog->name);
 	zfree(&prog->section_name);
 	zfree(&prog->insns);
 	zfree(&prog->reloc_desc);
@@ -293,26 +295,27 @@ static void bpf_program__exit(struct bpf_program *prog)
 }
 
 static int
-bpf_program__init(void *data, size_t size, char *name, int idx,
-		    struct bpf_program *prog)
+bpf_program__init(void *data, size_t size, char *section_name, int idx,
+		  struct bpf_program *prog)
 {
 	if (size < sizeof(struct bpf_insn)) {
-		pr_warning("corrupted section '%s'\n", name);
+		pr_warning("corrupted section '%s'\n", section_name);
 		return -EINVAL;
 	}
 
 	bzero(prog, sizeof(*prog));
 
-	prog->section_name = strdup(name);
+	prog->section_name = strdup(section_name);
 	if (!prog->section_name) {
-		pr_warning("failed to alloc name for prog %s\n",
-			   name);
+		pr_warning("failed to alloc name for prog under section %s\n",
+			   section_name);
 		goto errout;
 	}
 
 	prog->insns = malloc(size);
 	if (!prog->insns) {
-		pr_warning("failed to alloc insns for %s\n", name);
+		pr_warning("failed to alloc insns for prog under section %s\n",
+			   section_name);
 		goto errout;
 	}
 	prog->insns_cnt = size / sizeof(struct bpf_insn);
@@ -331,12 +334,12 @@ errout:
 
 static int
 bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
-			char *name, int idx)
+			char *section_name, int idx)
 {
 	struct bpf_program prog, *progs;
 	int nr_progs, err;
 
-	err = bpf_program__init(data, size, name, idx, &prog);
+	err = bpf_program__init(data, size, section_name, idx, &prog);
 	if (err)
 		return err;
 
@@ -350,8 +353,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 		 * is still valid, so don't need special treat for
 		 * bpf_close_object().
 		 */
-		pr_warning("failed to alloc a new program '%s'\n",
-			   name);
+		pr_warning("failed to alloc a new program under section '%s'\n",
+			   section_name);
 		bpf_program__exit(&prog);
 		return -ENOMEM;
 	}
@@ -364,6 +367,54 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	return 0;
 }
 
+static int
+bpf_object__init_prog_names(struct bpf_object *obj)
+{
+	Elf_Data *symbols = obj->efile.symbols;
+	struct bpf_program *prog;
+	size_t pi, si;
+
+	for (pi = 0; pi < obj->nr_programs; pi++) {
+		char *name = NULL;
+
+		prog = &obj->programs[pi];
+
+		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
+		     si++) {
+			GElf_Sym sym;
+
+			if (!gelf_getsym(symbols, si, &sym))
+				continue;
+			if (sym.st_shndx != prog->idx)
+				continue;
+
+			name = elf_strptr(obj->efile.elf,
+					  obj->efile.strtabidx,
+					  sym.st_name);
+			if (!name) {
+				pr_warning("failed to get sym name string for prog %s\n",
+					   prog->section_name);
+				return -LIBBPF_ERRNO__LIBELF;
+			}
+		}
+
+		if (!name) {
+			pr_warning("failed to find sym for prog %s\n",
+				   prog->section_name);
+			return -EINVAL;
+		}
+
+		prog->name = strdup(name);
+		if (!prog->name) {
+			pr_warning("failed to allocate memory for prog sym %s\n",
+				   name);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
 static struct bpf_object *bpf_object__new(const char *path,
 					  void *obj_buf,
 					  size_t obj_buf_sz)
@@ -766,8 +817,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
-	if (obj->efile.maps_shndx >= 0)
+	if (obj->efile.maps_shndx >= 0) {
 		err = bpf_object__init_maps(obj);
+		if (err)
+			goto out;
+	}
+	err = bpf_object__init_prog_names(obj);
 out:
 	return err;
 }
@@ -870,11 +925,12 @@ bpf_object__create_maps(struct bpf_object *obj)
 		struct bpf_map_def *def = &obj->maps[i].def;
 		int *pfd = &obj->maps[i].fd;
 
-		*pfd = bpf_create_map(def->type,
-				      def->key_size,
-				      def->value_size,
-				      def->max_entries,
-				      0);
+		*pfd = bpf_create_map_name(def->type,
+					   obj->maps[i].name,
+					   def->key_size,
+					   def->value_size,
+					   def->max_entries,
+					   0);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
@@ -982,7 +1038,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(enum bpf_prog_type type, struct bpf_insn *insns,
+load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns,
 	     int insns_cnt, char *license, u32 kern_version, int *pfd)
 {
 	int ret;
@@ -995,8 +1051,8 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 	if (!log_buf)
 		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
 
-	ret = bpf_load_program(type, insns, insns_cnt, license,
-			       kern_version, log_buf, BPF_LOG_BUF_SIZE);
+	ret = bpf_load_program_name(type, name, insns, insns_cnt, license,
+				    kern_version, log_buf, BPF_LOG_BUF_SIZE);
 
 	if (ret >= 0) {
 		*pfd = ret;
@@ -1021,9 +1077,9 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		if (type != BPF_PROG_TYPE_KPROBE) {
 			int fd;
 
-			fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
-					      insns_cnt, license, kern_version,
-					      NULL, 0);
+			fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name,
+						   insns, insns_cnt, license,
+						   kern_version, NULL, 0);
 			if (fd >= 0) {
 				close(fd);
 				ret = -LIBBPF_ERRNO__PROGTYPE;
@@ -1067,8 +1123,8 @@ bpf_program__load(struct bpf_program *prog,
 			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
 				   prog->section_name, prog->instances.nr);
 		}
-		err = load_program(prog->type, prog->insns, prog->insns_cnt,
-				   license, kern_version, &fd);
+		err = load_program(prog->type, prog->name, prog->insns,
+				   prog->insns_cnt, license, kern_version, &fd);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1096,7 +1152,8 @@ bpf_program__load(struct bpf_program *prog,
 			continue;
 		}
 
-		err = load_program(prog->type, result.new_insn_ptr,
+		err = load_program(prog->type, prog->name,
+				   result.new_insn_ptr,
 				   result.new_insn_cnt,
 				   license, kern_version, &fd);
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index a0426147523d..290d5056c165 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6939,7 +6939,7 @@ static int create_map_in_map(void)
 		return inner_map_fd;
 	}
 
-	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
 					     sizeof(int), inner_map_fd, 1, 0);
 	if (outer_map_fd < 0)
 		printf("Failed to create array of maps '%s'!\n",
-- 
cgit v1.2.3


From 6e525d06674a21468b4e728ef880770a0ca5c60d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 27 Sep 2017 14:37:55 -0700
Subject: bpf: Swap the order of checking prog_info and map_info

This patch swaps the checking order.  It now checks the map_info
first and then prog_info.  It is a prep work for adding
test to the newly added fields (the map_ids of prog_info field
in particular).

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_progs.c | 58 +++++++++++++++++---------------
 1 file changed, 30 insertions(+), 28 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 11ee25cea227..31ae27dc8d04 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -316,6 +316,36 @@ static void test_bpf_obj_id(void)
 			error_cnt++;
 		assert(!err);
 
+		/* Insert a magic value to the map */
+		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
+		assert(map_fds[i] >= 0);
+		err = bpf_map_update_elem(map_fds[i], &array_key,
+					  &array_magic_value, 0);
+		assert(!err);
+
+		/* Check getting map info */
+		info_len = sizeof(struct bpf_map_info) * 2;
+		bzero(&map_infos[i], info_len);
+		err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
+					     &info_len);
+		if (CHECK(err ||
+			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
+			  map_infos[i].key_size != sizeof(__u32) ||
+			  map_infos[i].value_size != sizeof(__u64) ||
+			  map_infos[i].max_entries != 1 ||
+			  map_infos[i].map_flags != 0 ||
+			  info_len != sizeof(struct bpf_map_info),
+			  "get-map-info(fd)",
+			  "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
+			  err, errno,
+			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
+			  info_len, sizeof(struct bpf_map_info),
+			  map_infos[i].key_size,
+			  map_infos[i].value_size,
+			  map_infos[i].max_entries,
+			  map_infos[i].map_flags))
+			goto done;
+
 		/* Check getting prog info */
 		info_len = sizeof(struct bpf_prog_info) * 2;
 		bzero(&prog_infos[i], info_len);
@@ -347,34 +377,6 @@ static void test_bpf_obj_id(void)
 			  !!memcmp(xlated_insns, zeros, sizeof(zeros))))
 			goto done;
 
-		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
-		assert(map_fds[i] >= 0);
-		err = bpf_map_update_elem(map_fds[i], &array_key,
-					  &array_magic_value, 0);
-		assert(!err);
-
-		/* Check getting map info */
-		info_len = sizeof(struct bpf_map_info) * 2;
-		bzero(&map_infos[i], info_len);
-		err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
-					     &info_len);
-		if (CHECK(err ||
-			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
-			  map_infos[i].key_size != sizeof(__u32) ||
-			  map_infos[i].value_size != sizeof(__u64) ||
-			  map_infos[i].max_entries != 1 ||
-			  map_infos[i].map_flags != 0 ||
-			  info_len != sizeof(struct bpf_map_info),
-			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
-			  err, errno,
-			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
-			  info_len, sizeof(struct bpf_map_info),
-			  map_infos[i].key_size,
-			  map_infos[i].value_size,
-			  map_infos[i].max_entries,
-			  map_infos[i].map_flags))
-			goto done;
 	}
 
 	/* Check bpf_prog_get_next_id() */
-- 
cgit v1.2.3


From 3a8ad560a9674235d1dd2e174434f540924e249f Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 27 Sep 2017 14:37:56 -0700
Subject: bpf: Test new fields in bpf_attr and bpf_{prog, map}_info

This patch tests newly added fields of the bpf_attr,
bpf_prog_info and bpf_map_info.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_progs.c | 143 ++++++++++++++++++++++++++++---
 1 file changed, 132 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 31ae27dc8d04..69427531408d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <time.h>
 
 #include <linux/types.h>
 typedef __u16 __sum16;
@@ -19,6 +20,8 @@ typedef __u16 __sum16;
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
 
 #include <sys/wait.h>
 #include <sys/resource.h>
@@ -273,16 +276,26 @@ static void test_bpf_obj_id(void)
 	const int nr_iters = 2;
 	const char *file = "./test_obj_id.o";
 	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	const char *expected_prog_name = "test_obj_id";
+	const char *expected_map_name = "test_map_id";
+	const __u64 nsec_per_sec = 1000000000;
 
 	struct bpf_object *objs[nr_iters];
 	int prog_fds[nr_iters], map_fds[nr_iters];
 	/* +1 to test for the info_len returned by kernel */
 	struct bpf_prog_info prog_infos[nr_iters + 1];
 	struct bpf_map_info map_infos[nr_iters + 1];
+	/* Each prog only uses one map. +1 to test nr_map_ids
+	 * returned by kernel.
+	 */
+	__u32 map_ids[nr_iters + 1];
 	char jited_insns[128], xlated_insns[128], zeros[128];
 	__u32 i, next_id, info_len, nr_id_found, duration = 0;
+	struct timespec real_time_ts, boot_time_ts;
 	int sysctl_fd, jit_enabled = 0, err = 0;
 	__u64 array_value;
+	uid_t my_uid = getuid();
+	time_t now, load_time;
 
 	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
 	if (sysctl_fd != -1) {
@@ -307,6 +320,7 @@ static void test_bpf_obj_id(void)
 	/* Check bpf_obj_get_info_by_fd() */
 	bzero(zeros, sizeof(zeros));
 	for (i = 0; i < nr_iters; i++) {
+		now = time(NULL);
 		err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
 				    &objs[i], &prog_fds[i]);
 		/* test_obj_id.o is a dumb prog. It should never fail
@@ -334,16 +348,18 @@ static void test_bpf_obj_id(void)
 			  map_infos[i].value_size != sizeof(__u64) ||
 			  map_infos[i].max_entries != 1 ||
 			  map_infos[i].map_flags != 0 ||
-			  info_len != sizeof(struct bpf_map_info),
+			  info_len != sizeof(struct bpf_map_info) ||
+			  strcmp((char *)map_infos[i].name, expected_map_name),
 			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
+			  "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
 			  err, errno,
 			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
 			  info_len, sizeof(struct bpf_map_info),
 			  map_infos[i].key_size,
 			  map_infos[i].value_size,
 			  map_infos[i].max_entries,
-			  map_infos[i].map_flags))
+			  map_infos[i].map_flags,
+			  map_infos[i].name, expected_map_name))
 			goto done;
 
 		/* Check getting prog info */
@@ -355,8 +371,16 @@ static void test_bpf_obj_id(void)
 		prog_infos[i].jited_prog_len = sizeof(jited_insns);
 		prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
 		prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
+		prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
+		prog_infos[i].nr_map_ids = 2;
+		err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
+		assert(!err);
+		err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
+		assert(!err);
 		err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
 					     &info_len);
+		load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
+			+ (prog_infos[i].load_time / nsec_per_sec);
 		if (CHECK(err ||
 			  prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
 			  info_len != sizeof(struct bpf_prog_info) ||
@@ -364,9 +388,14 @@ static void test_bpf_obj_id(void)
 			  (jit_enabled &&
 			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
 			  !prog_infos[i].xlated_prog_len ||
-			  !memcmp(xlated_insns, zeros, sizeof(zeros)),
+			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
+			  load_time < now - 60 || load_time > now + 60 ||
+			  prog_infos[i].created_by_uid != my_uid ||
+			  prog_infos[i].nr_map_ids != 1 ||
+			  *(int *)prog_infos[i].map_ids != map_infos[i].id ||
+			  strcmp((char *)prog_infos[i].name, expected_prog_name),
 			  "get-prog-info(fd)",
-			  "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d\n",
+			  "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
 			  err, errno, i,
 			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
 			  info_len, sizeof(struct bpf_prog_info),
@@ -374,9 +403,13 @@ static void test_bpf_obj_id(void)
 			  prog_infos[i].jited_prog_len,
 			  prog_infos[i].xlated_prog_len,
 			  !!memcmp(jited_insns, zeros, sizeof(zeros)),
-			  !!memcmp(xlated_insns, zeros, sizeof(zeros))))
+			  !!memcmp(xlated_insns, zeros, sizeof(zeros)),
+			  load_time, now,
+			  prog_infos[i].created_by_uid, my_uid,
+			  prog_infos[i].nr_map_ids, 1,
+			  *(int *)prog_infos[i].map_ids, map_infos[i].id,
+			  prog_infos[i].name, expected_prog_name))
 			goto done;
-
 	}
 
 	/* Check bpf_prog_get_next_id() */
@@ -384,6 +417,7 @@ static void test_bpf_obj_id(void)
 	next_id = 0;
 	while (!bpf_prog_get_next_id(next_id, &next_id)) {
 		struct bpf_prog_info prog_info = {};
+		__u32 saved_map_id;
 		int prog_fd;
 
 		info_len = sizeof(prog_info);
@@ -406,16 +440,33 @@ static void test_bpf_obj_id(void)
 
 		nr_id_found++;
 
+		/* Negative test:
+		 * prog_info.nr_map_ids = 1
+		 * prog_info.map_ids = NULL
+		 */
+		prog_info.nr_map_ids = 1;
+		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+		if (CHECK(!err || errno != EFAULT,
+			  "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
+			  err, errno, EFAULT))
+			break;
+		bzero(&prog_info, sizeof(prog_info));
+		info_len = sizeof(prog_info);
+
+		saved_map_id = *(int *)(prog_infos[i].map_ids);
+		prog_info.map_ids = prog_infos[i].map_ids;
+		prog_info.nr_map_ids = 2;
 		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
 		prog_infos[i].jited_prog_insns = 0;
 		prog_infos[i].xlated_prog_insns = 0;
 		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
-		      memcmp(&prog_info, &prog_infos[i], info_len),
+		      memcmp(&prog_info, &prog_infos[i], info_len) ||
+		      *(int *)prog_info.map_ids != saved_map_id,
 		      "get-prog-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%lu) memcmp %d\n",
+		      "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n",
 		      err, errno, info_len, sizeof(struct bpf_prog_info),
-		      memcmp(&prog_info, &prog_infos[i], info_len));
-
+		      memcmp(&prog_info, &prog_infos[i], info_len),
+		      *(int *)prog_info.map_ids, saved_map_id);
 		close(prog_fd);
 	}
 	CHECK(nr_id_found != nr_iters,
@@ -497,6 +548,75 @@ static void test_pkt_md_access(void)
 	bpf_object__close(obj);
 }
 
+static void test_obj_name(void)
+{
+	struct {
+		const char *name;
+		int success;
+		int expected_errno;
+	} tests[] = {
+		{ "", 1, 0 },
+		{ "_123456789ABCDE", 1, 0 },
+		{ "_123456789ABCDEF", 0, EINVAL },
+		{ "_123456789ABCD\n", 0, EINVAL },
+	};
+	struct bpf_insn prog[] = {
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	__u32 duration = 0;
+	int i;
+
+	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+		size_t name_len = strlen(tests[i].name) + 1;
+		union bpf_attr attr;
+		size_t ncopy;
+		int fd;
+
+		/* test different attr.prog_name during BPF_PROG_LOAD */
+		ncopy = name_len < sizeof(attr.prog_name) ?
+			name_len : sizeof(attr.prog_name);
+		bzero(&attr, sizeof(attr));
+		attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+		attr.insn_cnt = 2;
+		attr.insns = ptr_to_u64(prog);
+		attr.license = ptr_to_u64("");
+		memcpy(attr.prog_name, tests[i].name, ncopy);
+
+		fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+		CHECK((tests[i].success && fd < 0) ||
+		      (!tests[i].success && fd != -1) ||
+		      (!tests[i].success && errno != tests[i].expected_errno),
+		      "check-bpf-prog-name",
+		      "fd %d(%d) errno %d(%d)\n",
+		       fd, tests[i].success, errno, tests[i].expected_errno);
+
+		if (fd != -1)
+			close(fd);
+
+		/* test different attr.map_name during BPF_MAP_CREATE */
+		ncopy = name_len < sizeof(attr.map_name) ?
+			name_len : sizeof(attr.map_name);
+		bzero(&attr, sizeof(attr));
+		attr.map_type = BPF_MAP_TYPE_ARRAY;
+		attr.key_size = 4;
+		attr.value_size = 4;
+		attr.max_entries = 1;
+		attr.map_flags = 0;
+		memcpy(attr.map_name, tests[i].name, ncopy);
+		fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
+		CHECK((tests[i].success && fd < 0) ||
+		      (!tests[i].success && fd != -1) ||
+		      (!tests[i].success && errno != tests[i].expected_errno),
+		      "check-bpf-map-name",
+		      "fd %d(%d) errno %d(%d)\n",
+		      fd, tests[i].success, errno, tests[i].expected_errno);
+
+		if (fd != -1)
+			close(fd);
+	}
+}
+
 int main(void)
 {
 	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
@@ -509,6 +629,7 @@ int main(void)
 	test_tcp_estats();
 	test_bpf_obj_id();
 	test_pkt_md_access();
+	test_obj_name();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
-- 
cgit v1.2.3


From 6227efc1a20b24a21ce8e9122c0569696d644aff Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 2 Oct 2017 12:05:29 +0200
Subject: selftests: rtnetlink.sh: add vxlan and fou test cases

fou test lifted from ip-fou man page.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 96 ++++++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a048f7a5f94c..62c87da92770 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -332,6 +332,101 @@ kci_test_vrf()
 	echo "PASS: vrf"
 }
 
+kci_test_encap_vxlan()
+{
+	ret=0
+	vxlan="test-vxlan0"
+	vlan="test-vlan0"
+	testns="$1"
+
+	ip netns exec "$testns" ip link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
+		dev "$devdummy" dstport 4789 2>/dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: can't add vxlan interface, skipping test"
+		return 0
+	fi
+	check_err $?
+
+	ip netns exec "$testns" ip addr add 10.2.11.49/24 dev "$vxlan"
+	check_err $?
+
+	ip netns exec "$testns" ip link set up dev "$vxlan"
+	check_err $?
+
+	ip netns exec "$testns" ip link add link "$vxlan" name "$vlan" type vlan id 1
+	check_err $?
+
+	ip netns exec "$testns" ip link del "$vxlan"
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: vxlan"
+		return 1
+	fi
+	echo "PASS: vxlan"
+}
+
+kci_test_encap_fou()
+{
+	ret=0
+	name="test-fou"
+	testns="$1"
+
+	ip fou help 2>&1 |grep -q 'Usage: ip fou'
+	if [ $? -ne 0 ];then
+		echo "SKIP: fou: iproute2 too old"
+		return 1
+	fi
+
+	ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null
+	if [ $? -ne 0 ];then
+		echo "FAIL: can't add fou port 7777, skipping test"
+		return 1
+	fi
+
+	ip netns exec "$testns" ip fou add port 8888 ipproto 4
+	check_err $?
+
+	ip netns exec "$testns" ip fou del port 9999 2>/dev/null
+	check_fail $?
+
+	ip netns exec "$testns" ip fou del port 7777
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: fou"
+		return 1
+	fi
+
+	echo "PASS: fou"
+}
+
+# test various encap methods, use netns to avoid unwanted interference
+kci_test_encap()
+{
+	testns="testns"
+	ret=0
+
+	ip netns add "$testns"
+	if [ $? -ne 0 ]; then
+		echo "SKIP encap tests: cannot add net namespace $testns"
+		return 1
+	fi
+
+	ip netns exec "$testns" ip link set lo up
+	check_err $?
+
+	ip netns exec "$testns" ip link add name "$devdummy" type dummy
+	check_err $?
+	ip netns exec "$testns" ip link set "$devdummy" up
+	check_err $?
+
+	kci_test_encap_vxlan "$testns"
+	kci_test_encap_fou "$testns"
+
+	ip netns del "$testns"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -348,6 +443,7 @@ kci_test_rtnl()
 	kci_test_addrlabel
 	kci_test_ifalias
 	kci_test_vrf
+	kci_test_encap
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From fe97d28704147ba72f7d7859909f80b4bb5a17d4 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Wed, 20 Sep 2017 10:00:36 +0800
Subject: ACPICA: Restructure/cleanup all string-to-integer conversion
 functions

ACPICA commit 610046d444ad781cc36673bf1f030abe50cbc61f

Improve adherence to ACPI spec for implicit and explicit conversions
Adds octal support for constants in ASL code
Adds integer overflow errors for constants during ASL compilation
Eliminates most of the existing complex flags parameters
Simplify support for implicit/explicit runtime conversions
Adds one new file, utilities/utstrsuppt.c

Link: https://github.com/acpica/acpica/commit/610046d444ad
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/Makefile             |   1 +
 drivers/acpi/acpica/acinterp.h           |   6 +-
 drivers/acpi/acpica/acutils.h            |  31 ++-
 drivers/acpi/acpica/dbconvert.c          |   5 +-
 drivers/acpi/acpica/dswexec.c            |   2 +-
 drivers/acpi/acpica/exconcat.c           |   2 +-
 drivers/acpi/acpica/exconvrt.c           |  30 ++-
 drivers/acpi/acpica/exmisc.c             |   2 +-
 drivers/acpi/acpica/exresop.c            |   2 +-
 drivers/acpi/acpica/nsconvert.c          |   4 +-
 drivers/acpi/acpica/utstrsuppt.c         | 417 ++++++++++++++++++++++++++++++
 drivers/acpi/acpica/utstrtoul64.c        | 420 +++++++++++++++----------------
 include/acpi/acexcep.h                   |  16 +-
 tools/power/acpi/tools/acpidump/Makefile |   1 +
 tools/power/acpi/tools/acpidump/apdump.c |   3 +-
 tools/power/acpi/tools/acpidump/apmain.c |   4 +-
 16 files changed, 690 insertions(+), 256 deletions(-)
 create mode 100644 drivers/acpi/acpica/utstrsuppt.c

(limited to 'tools')

diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile
index 1709551bc4aa..2d09b0249ac8 100644
--- a/drivers/acpi/acpica/Makefile
+++ b/drivers/acpi/acpica/Makefile
@@ -177,6 +177,7 @@ acpi-y +=		\
 	utresrc.o	\
 	utstate.o	\
 	utstring.o	\
+	utstrsuppt.o	\
 	utstrtoul64.o	\
 	utxface.o	\
 	utxfinit.o	\
diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h
index 29a863c85318..29555c8789a3 100644
--- a/drivers/acpi/acpica/acinterp.h
+++ b/drivers/acpi/acpica/acinterp.h
@@ -101,7 +101,8 @@ typedef const struct acpi_exdump_info {
  */
 acpi_status
 acpi_ex_convert_to_integer(union acpi_operand_object *obj_desc,
-			   union acpi_operand_object **result_desc, u32 flags);
+			   union acpi_operand_object **result_desc,
+			   u32 implicit_conversion);
 
 acpi_status
 acpi_ex_convert_to_buffer(union acpi_operand_object *obj_desc,
@@ -424,9 +425,6 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 			     struct acpi_walk_state *walk_state,
 			     u8 implicit_conversion);
 
-#define ACPI_IMPLICIT_CONVERSION        TRUE
-#define ACPI_NO_IMPLICIT_CONVERSION     FALSE
-
 /*
  * exstoren - resolve/store object
  */
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 745134ade35f..7a568c604a75 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -141,6 +141,11 @@ extern const char *acpi_gbl_ptyp_decode[];
 #define ACPI_MSG_SUFFIX \
 	acpi_os_printf (" (%8.8X/%s-%u)\n", ACPI_CA_VERSION, module_name, line_number)
 
+/* Flags to indicate implicit or explicit string-to-integer conversion */
+
+#define ACPI_IMPLICIT_CONVERSION        TRUE
+#define ACPI_NO_IMPLICIT_CONVERSION     FALSE
+
 /* Types for Resource descriptor entries */
 
 #define ACPI_INVALID_RESOURCE           0
@@ -197,15 +202,29 @@ void acpi_ut_strlwr(char *src_string);
 
 int acpi_ut_stricmp(char *string1, char *string2);
 
-acpi_status acpi_ut_strtoul64(char *string, u32 flags, u64 *ret_integer);
+/*
+ * utstrsuppt - string-to-integer conversion support functions
+ */
+acpi_status acpi_ut_convert_octal_string(char *string, u64 *return_value);
+
+acpi_status acpi_ut_convert_decimal_string(char *string, u64 *return_value_ptr);
+
+acpi_status acpi_ut_convert_hex_string(char *string, u64 *return_value_ptr);
+
+char acpi_ut_remove_leading_zeros(char **string);
+
+u8 acpi_ut_detect_hex_prefix(char **string);
+
+u8 acpi_ut_detect_octal_prefix(char **string);
 
 /*
- * Values for Flags above
- * Note: LIMIT values correspond to acpi_gbl_integer_byte_width values (4/8)
+ * utstrtoul64 - string-to-integer conversion functions
  */
-#define ACPI_STRTOUL_32BIT          0x04	/* 4 bytes */
-#define ACPI_STRTOUL_64BIT          0x08	/* 8 bytes */
-#define ACPI_STRTOUL_BASE16         0x10	/* Default: Base10/16 */
+acpi_status acpi_ut_strtoul64(char *string, u64 *ret_integer);
+
+u64 acpi_ut_explicit_strtoul64(char *string);
+
+u64 acpi_ut_implicit_strtoul64(char *string);
 
 /*
  * utglobal - Global data structures and procedures
diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c
index 857dbc43a9b1..32d546f0db2f 100644
--- a/drivers/acpi/acpica/dbconvert.c
+++ b/drivers/acpi/acpica/dbconvert.c
@@ -277,10 +277,7 @@ acpi_db_convert_to_object(acpi_object_type type,
 	default:
 
 		object->type = ACPI_TYPE_INTEGER;
-		status = acpi_ut_strtoul64(string,
-					   (acpi_gbl_integer_byte_width |
-					    ACPI_STRTOUL_BASE16),
-					   &object->integer.value);
+		status = acpi_ut_strtoul64(string, &object->integer.value);
 		break;
 	}
 
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index 20d7744b06ae..22f45d090733 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -134,7 +134,7 @@ acpi_ds_get_predicate_value(struct acpi_walk_state *walk_state,
 	 * object. Implicitly convert the argument if necessary.
 	 */
 	status = acpi_ex_convert_to_integer(obj_desc, &local_obj_desc,
-					    ACPI_STRTOUL_BASE16);
+					    ACPI_IMPLICIT_CONVERSION);
 	if (ACPI_FAILURE(status)) {
 		goto cleanup;
 	}
diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c
index 76bfb7dcae2f..59b8de2f07d3 100644
--- a/drivers/acpi/acpica/exconcat.c
+++ b/drivers/acpi/acpica/exconcat.c
@@ -156,7 +156,7 @@ acpi_ex_do_concatenate(union acpi_operand_object *operand0,
 
 		status =
 		    acpi_ex_convert_to_integer(local_operand1, &temp_operand1,
-					       ACPI_STRTOUL_BASE16);
+					       ACPI_IMPLICIT_CONVERSION);
 		break;
 
 	case ACPI_TYPE_BUFFER:
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index f71028e334ee..23ebadb06a95 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -57,10 +57,10 @@ acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 max_length);
  *
  * FUNCTION:    acpi_ex_convert_to_integer
  *
- * PARAMETERS:  obj_desc        - Object to be converted. Must be an
- *                                Integer, Buffer, or String
- *              result_desc     - Where the new Integer object is returned
- *              flags           - Used for string conversion
+ * PARAMETERS:  obj_desc            - Object to be converted. Must be an
+ *                                    Integer, Buffer, or String
+ *              result_desc         - Where the new Integer object is returned
+ *              implicit_conversion - Used for string conversion
  *
  * RETURN:      Status
  *
@@ -70,14 +70,14 @@ acpi_ex_convert_to_ascii(u64 integer, u16 base, u8 *string, u8 max_length);
 
 acpi_status
 acpi_ex_convert_to_integer(union acpi_operand_object *obj_desc,
-			   union acpi_operand_object **result_desc, u32 flags)
+			   union acpi_operand_object **result_desc,
+			   u32 implicit_conversion)
 {
 	union acpi_operand_object *return_desc;
 	u8 *pointer;
 	u64 result;
 	u32 i;
 	u32 count;
-	acpi_status status;
 
 	ACPI_FUNCTION_TRACE_PTR(ex_convert_to_integer, obj_desc);
 
@@ -123,12 +123,18 @@ acpi_ex_convert_to_integer(union acpi_operand_object *obj_desc,
 		 * hexadecimal as per the ACPI specification. The only exception (as
 		 * of ACPI 3.0) is that the to_integer() operator allows both decimal
 		 * and hexadecimal strings (hex prefixed with "0x").
+		 *
+		 * Explicit conversion is used only by to_integer.
+		 * All other string-to-integer conversions are implicit conversions.
 		 */
-		status = acpi_ut_strtoul64(ACPI_CAST_PTR(char, pointer),
-					   (acpi_gbl_integer_byte_width |
-					    flags), &result);
-		if (ACPI_FAILURE(status)) {
-			return_ACPI_STATUS(status);
+		if (implicit_conversion) {
+			result =
+			    acpi_ut_implicit_strtoul64(ACPI_CAST_PTR
+						       (char, pointer));
+		} else {
+			result =
+			    acpi_ut_explicit_strtoul64(ACPI_CAST_PTR
+						       (char, pointer));
 		}
 		break;
 
@@ -631,7 +637,7 @@ acpi_ex_convert_to_target_type(acpi_object_type destination_type,
 			 */
 			status =
 			    acpi_ex_convert_to_integer(source_desc, result_desc,
-						       ACPI_STRTOUL_BASE16);
+						       ACPI_IMPLICIT_CONVERSION);
 			break;
 
 		case ACPI_TYPE_STRING:
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index 1e7649ce0a7b..dbad3ebd7df5 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -330,7 +330,7 @@ acpi_ex_do_logical_op(u16 opcode,
 	case ACPI_TYPE_INTEGER:
 
 		status = acpi_ex_convert_to_integer(operand1, &local_operand1,
-						    ACPI_STRTOUL_BASE16);
+						    ACPI_IMPLICIT_CONVERSION);
 		break;
 
 	case ACPI_TYPE_STRING:
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index c4852429e2ff..1c7c9962b0de 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -415,7 +415,7 @@ acpi_ex_resolve_operands(u16 opcode,
 			 * Known as "Implicit Source Operand Conversion"
 			 */
 			status = acpi_ex_convert_to_integer(obj_desc, stack_ptr,
-							    ACPI_STRTOUL_BASE16);
+							    ACPI_IMPLICIT_CONVERSION);
 			if (ACPI_FAILURE(status)) {
 				if (status == AE_TYPE) {
 					ACPI_ERROR((AE_INFO,
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index e4a7da8a11f0..539d775bbc92 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -78,8 +78,8 @@ acpi_ns_convert_to_integer(union acpi_operand_object *original_object,
 
 		/* String-to-Integer conversion */
 
-		status = acpi_ut_strtoul64(original_object->string.pointer,
-					   acpi_gbl_integer_byte_width, &value);
+		status =
+		    acpi_ut_strtoul64(original_object->string.pointer, &value);
 		if (ACPI_FAILURE(status)) {
 			return (status);
 		}
diff --git a/drivers/acpi/acpica/utstrsuppt.c b/drivers/acpi/acpica/utstrsuppt.c
new file mode 100644
index 000000000000..ca41f037fd9a
--- /dev/null
+++ b/drivers/acpi/acpica/utstrsuppt.c
@@ -0,0 +1,417 @@
+/*******************************************************************************
+ *
+ * Module Name: utstrsuppt - string-to-integer conversion support functions
+ *
+ ******************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2017, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+
+#define _COMPONENT          ACPI_UTILITIES
+ACPI_MODULE_NAME("utstrsuppt")
+
+/* Local prototypes */
+static acpi_status
+acpi_ut_insert_digit(u64 *accumulated_value, u32 base, int ascii_digit);
+
+static acpi_status
+acpi_ut_strtoul_multiply64(u64 multiplicand, u64 multiplier, u64 *out_product);
+
+static acpi_status
+acpi_ut_strtoul_add64(u64 addend1, u64 addend2, u64 *out_sum);
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_convert_octal_string
+ *
+ * PARAMETERS:  string                  - Null terminated input string
+ *              return_value_ptr        - Where the converted value is returned
+ *
+ * RETURN:      Status and 64-bit converted integer
+ *
+ * DESCRIPTION: Performs a base 8 conversion of the input string to an
+ *              integer value, either 32 or 64 bits.
+ *
+ * NOTE:        Maximum 64-bit unsigned octal value is 01777777777777777777777
+ *              Maximum 32-bit unsigned octal value is 037777777777
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ut_convert_octal_string(char *string, u64 *return_value_ptr)
+{
+	u64 accumulated_value = 0;
+	acpi_status status = AE_OK;
+
+	/* Convert each ASCII byte in the input string */
+
+	while (*string) {
+
+		/* Must be ASCII 0-7, otherwise terminate with no error */
+
+		if (!(ACPI_IS_OCTAL_DIGIT(*string))) {
+			break;
+		}
+
+		/* Convert and insert this octal digit into the accumulator */
+
+		status = acpi_ut_insert_digit(&accumulated_value, 8, *string);
+		if (ACPI_FAILURE(status)) {
+			status = AE_OCTAL_OVERFLOW;
+			break;
+		}
+
+		string++;
+	}
+
+	/* Always return the value that has been accumulated */
+
+	*return_value_ptr = accumulated_value;
+	return (status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_convert_decimal_string
+ *
+ * PARAMETERS:  string                  - Null terminated input string
+ *              return_value_ptr        - Where the converted value is returned
+ *
+ * RETURN:      Status and 64-bit converted integer
+ *
+ * DESCRIPTION: Performs a base 10 conversion of the input string to an
+ *              integer value, either 32 or 64 bits.
+ *
+ * NOTE:        Maximum 64-bit unsigned decimal value is 18446744073709551615
+ *              Maximum 32-bit unsigned decimal value is 4294967295
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ut_convert_decimal_string(char *string, u64 *return_value_ptr)
+{
+	u64 accumulated_value = 0;
+	acpi_status status = AE_OK;
+
+	/* Convert each ASCII byte in the input string */
+
+	while (*string) {
+
+		/* Must be ASCII 0-9, otherwise terminate with no error */
+
+		if (!isdigit(*string)) {
+			break;
+		}
+
+		/* Convert and insert this decimal digit into the accumulator */
+
+		status = acpi_ut_insert_digit(&accumulated_value, 10, *string);
+		if (ACPI_FAILURE(status)) {
+			status = AE_DECIMAL_OVERFLOW;
+			break;
+		}
+
+		string++;
+	}
+
+	/* Always return the value that has been accumulated */
+
+	*return_value_ptr = accumulated_value;
+	return (status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_convert_hex_string
+ *
+ * PARAMETERS:  string                  - Null terminated input string
+ *              return_value_ptr        - Where the converted value is returned
+ *
+ * RETURN:      Status and 64-bit converted integer
+ *
+ * DESCRIPTION: Performs a base 16 conversion of the input string to an
+ *              integer value, either 32 or 64 bits.
+ *
+ * NOTE:        Maximum 64-bit unsigned hex value is 0xFFFFFFFFFFFFFFFF
+ *              Maximum 32-bit unsigned hex value is 0xFFFFFFFF
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ut_convert_hex_string(char *string, u64 *return_value_ptr)
+{
+	u64 accumulated_value = 0;
+	acpi_status status = AE_OK;
+
+	/* Convert each ASCII byte in the input string */
+
+	while (*string) {
+
+		/* Must be ASCII A-F, a-f, or 0-9, otherwise terminate with no error */
+
+		if (!isxdigit(*string)) {
+			break;
+		}
+
+		/* Convert and insert this hex digit into the accumulator */
+
+		status = acpi_ut_insert_digit(&accumulated_value, 16, *string);
+		if (ACPI_FAILURE(status)) {
+			status = AE_HEX_OVERFLOW;
+			break;
+		}
+
+		string++;
+	}
+
+	/* Always return the value that has been accumulated */
+
+	*return_value_ptr = accumulated_value;
+	return (status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_remove_leading_zeros
+ *
+ * PARAMETERS:  string                  - Pointer to input ASCII string
+ *
+ * RETURN:      Next character after the leading zeros. This behavior may be
+ *              Used by the caller to detect end-of-string.
+ *
+ * DESCRIPTION: Remove all leading zeros in the input string. Return the
+ *              next character after the final zero to check for the end
+ *              of the string (NULL terminator).
+ *
+ ******************************************************************************/
+
+char acpi_ut_remove_leading_zeros(char **string)
+{
+	/* Skip all leading zeros */
+
+	while (**string == ACPI_ASCII_ZERO) {
+		*string += 1;
+	}
+
+	return (**string);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_detect_hex_prefix
+ *
+ * PARAMETERS:  string                  - Pointer to input ASCII string
+ *
+ * RETURN:      TRUE if a 0x prefix was found
+ *
+ * DESCRIPTION: Detect and remove a hex 0x prefix
+ *
+ ******************************************************************************/
+
+u8 acpi_ut_detect_hex_prefix(char **string)
+{
+
+	if ((**string == ACPI_ASCII_ZERO) &&
+	    (tolower((int)*(*string + 1)) == 'x')) {
+		*string += 2;	/* Go past the leading 0x */
+		return (TRUE);
+	}
+
+	return (FALSE);		/* Not a hex string */
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_detect_octal_prefix
+ *
+ * PARAMETERS:  string                  - Pointer to input ASCII string
+ *
+ * RETURN:      True if an octal 0 prefix was found
+ *
+ * DESCRIPTION: Detect and remove an octal prefix (zero)
+ *
+ ******************************************************************************/
+
+u8 acpi_ut_detect_octal_prefix(char **string)
+{
+
+	if (**string == ACPI_ASCII_ZERO) {
+		*string += 1;	/* Go past the leading 0 */
+		return (TRUE);
+	}
+
+	return (FALSE);		/* Not an octal string */
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_insert_digit
+ *
+ * PARAMETERS:  accumulated_value       - Current value of the integer value
+ *                                        accumulator. The New value is
+ *                                        returned here.
+ *              base                    - Radix, either 8/10/16 supported
+ *              ascii_digit             - ASCII single digit to be inserted
+ *
+ * RETURN:      Status and result of convert/insert operation. The only
+ *              exception is numeric overflow of either the multiply or the
+ *              add operations.
+ *
+ * DESCRIPTION: Generic conversion and insertion function for all bases:
+ *
+ *              1) Multiply the current accumulated converted value by the
+ *              base in order to make room for the new character.
+ *
+ *              2) Add the current accumulated/converted value the new
+ *              character (after the character has been converted to a binary
+ *              value).
+ *
+ *              Note: The only possible exception indicates an integer
+ *              overflow (AE_NUMERIC_OVERFLOW)
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ut_insert_digit(u64 *accumulated_value, u32 base, int ascii_digit)
+{
+	acpi_status status;
+	u64 product;
+
+	/* Make room in the accumulated value for the incoming digit */
+
+	status = acpi_ut_strtoul_multiply64(*accumulated_value, base, &product);
+	if (ACPI_FAILURE(status)) {
+		return (status);
+	}
+
+	/* Add in the new digit, and store to the caller's accumulated value */
+
+	status =
+	    acpi_ut_strtoul_add64(product,
+				  acpi_ut_ascii_char_to_hex(ascii_digit),
+				  accumulated_value);
+	if (ACPI_FAILURE(status)) {
+		return (status);
+	}
+
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_strtoul_multiply64
+ *
+ * PARAMETERS:  multiplicand            - Current accumulated converted integer
+ *              multiplier              - Base/Radix
+ *              out_product             - Where the product is returned
+ *
+ * RETURN:      Status and 64-bit product
+ *
+ * DESCRIPTION: Multiply two 64-bit values, with checking for 64-bit overflow as
+ *              well as 32-bit overflow if necessary (if the current global
+ *              integer width is 32).
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ut_strtoul_multiply64(u64 multiplicand, u64 multiplier, u64 *out_product)
+{
+	u64 val;
+
+	/* Exit if either operand is zero */
+
+	*out_product = 0;
+	if (!multiplicand || !multiplier) {
+		return (AE_OK);
+	}
+
+	/* Check for 64-bit overflow before the actual multiplication */
+
+	acpi_ut_short_divide(ACPI_UINT64_MAX, (u32)multiplier, &val, NULL);
+	if (multiplicand > val) {
+		return (AE_NUMERIC_OVERFLOW);
+	}
+
+	val = multiplicand * multiplier;
+
+	/* Check for 32-bit overflow if necessary */
+
+	if ((acpi_gbl_integer_bit_width == 32) && (val > ACPI_UINT32_MAX)) {
+		return (AE_NUMERIC_OVERFLOW);
+	}
+
+	*out_product = val;
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_strtoul_add64
+ *
+ * PARAMETERS:  addend1                 - Current accumulated converted integer
+ *              addend2                 - New hex value/char
+ *              out_sum                 - Where sum is returned (Accumulator)
+ *
+ * RETURN:      Status and 64-bit sum
+ *
+ * DESCRIPTION: Add two 64-bit values, with checking for 64-bit overflow as
+ *              well as 32-bit overflow if necessary (if the current global
+ *              integer width is 32).
+ *
+ ******************************************************************************/
+
+static acpi_status acpi_ut_strtoul_add64(u64 addend1, u64 addend2, u64 *out_sum)
+{
+	u64 sum;
+
+	/* Check for 64-bit overflow before the actual addition */
+
+	if ((addend1 > 0) && (addend2 > (ACPI_UINT64_MAX - addend1))) {
+		return (AE_NUMERIC_OVERFLOW);
+	}
+
+	sum = addend1 + addend2;
+
+	/* Check for 32-bit overflow if necessary */
+
+	if ((acpi_gbl_integer_bit_width == 32) && (sum > ACPI_UINT32_MAX)) {
+		return (AE_NUMERIC_OVERFLOW);
+	}
+
+	*out_sum = sum;
+	return (AE_OK);
+}
diff --git a/drivers/acpi/acpica/utstrtoul64.c b/drivers/acpi/acpica/utstrtoul64.c
index 9633ee142855..e5a2df3f16e5 100644
--- a/drivers/acpi/acpica/utstrtoul64.c
+++ b/drivers/acpi/acpica/utstrtoul64.c
@@ -1,6 +1,7 @@
 /*******************************************************************************
  *
- * Module Name: utstrtoul64 - string to 64-bit integer support
+ * Module Name: utstrtoul64 - string-to-integer support for both 64-bit
+ *                            and 32-bit integers
  *
  ******************************************************************************/
 
@@ -44,152 +45,74 @@
 #include <acpi/acpi.h>
 #include "accommon.h"
 
-/*******************************************************************************
- *
- * The functions in this module satisfy the need for 64-bit string-to-integer
- * conversions on both 32-bit and 64-bit platforms.
- *
- ******************************************************************************/
-
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utstrtoul64")
 
-/* Local prototypes */
-static u64 acpi_ut_strtoul_base10(char *string, u32 flags);
-
-static u64 acpi_ut_strtoul_base16(char *string, u32 flags);
-
 /*******************************************************************************
  *
- * String conversion rules as written in the ACPI specification. The error
- * conditions and behavior are different depending on the type of conversion.
- *
+ * This module contains the external string to 64/32-bit unsigned integer
+ * conversion functions:
  *
- * Implicit data type conversion: string-to-integer
- * --------------------------------------------------
- *
- * Base is always 16. This is the ACPI_STRTOUL_BASE16 case.
- *
- * Example:
- *      Add ("BA98", Arg0, Local0)
- *
- * The integer is initialized to the value zero.
- * The ASCII string is interpreted as a hexadecimal constant.
- *
- *  1)  A "0x" prefix is not allowed. However, ACPICA allows this for
- *      compatibility with previous ACPICA. (NO ERROR)
- *
- *  2)  Terminates when the size of an integer is reached (32 or 64 bits).
- *      (NO ERROR)
+ *  1) Standard strtoul() function with 64-bit support. This is mostly used by
+ *      the iASL compiler.
+ *  2) Runtime "Explicit conversion" as defined in the ACPI specification.
+ *  3) Runtime "Implicit conversion" as defined in the ACPI specification.
  *
- *  3)  The first non-hex character terminates the conversion without error.
- *      (NO ERROR)
+ * Current users of this module:
  *
- *  4)  Conversion of a null (zero-length) string to an integer is not
- *      allowed. However, ACPICA allows this for compatibility with previous
- *      ACPICA. This conversion returns the value 0. (NO ERROR)
- *
- *
- * Explicit data type conversion:  to_integer() with string operand
- * ---------------------------------------------------------------
- *
- * Base is either 10 (default) or 16 (with 0x prefix)
- *
- * Examples:
- *      to_integer ("1000")
- *      to_integer ("0xABCD")
- *
- *  1)  Can be (must be) either a decimal or hexadecimal numeric string.
- *      A hex value must be prefixed by "0x" or it is interpreted as a decimal.
+ *  interpreter - Implicit and explicit conversions, GPE method names
+ *  debugger    - Command line input string conversion
+ *  iASL        - Main parser, conversion of constants to integers
+ *  iASL        - Data Table Compiler parser (constant math expressions)
+ *  iASL        - Preprocessor (constant math expressions)
+ *  acpi_dump   - Input table addresses
+ *  acpi_exec   - Testing of the acpi_ut_strtoul64 function
  *
- *  2)  The value must not exceed the maximum of an integer value. ACPI spec
- *      states the behavior is "unpredictable", so ACPICA matches the behavior
- *      of the implicit conversion case.(NO ERROR)
+ * Notes concerning users of these interfaces:
  *
- *  3)  Behavior on the first non-hex character is not specified by the ACPI
- *      spec, so ACPICA matches the behavior of the implicit conversion case
- *      and terminates. (NO ERROR)
+ *  acpi_gbl_integer_byte_width is used to set the 32/64 bit limit. This global
+ *  must be set to the proper width. For the core ACPICA code, the width
+ *  depends on the DSDT version. For iASL, the default width is 64 bits for
+ *  all parsers, but error checking is performed later to flag cases where
+ *  a 64-bit constant is wrongly defined in a 32-bit DSDT/SSDT.
  *
- *  4)  A null (zero-length) string is illegal.
- *      However, ACPICA allows this for compatibility with previous ACPICA.
- *      This conversion returns the value 0. (NO ERROR)
+ *  In ACPI, the only place where octal numbers are supported is within
+ *  the ASL language itself. There is no runtime support for octal.
  *
  ******************************************************************************/
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_strtoul64
  *
- * PARAMETERS:  string                  - Null terminated input string
- *              flags                   - Conversion info, see below
+ * PARAMETERS:  string                  - Null terminated input string.
+ *                                        Must be a valid pointer
  *              return_value            - Where the converted integer is
- *                                        returned
- *
- * RETURN:      Status and Converted value
- *
- * DESCRIPTION: Convert a string into an unsigned value. Performs either a
- *              32-bit or 64-bit conversion, depending on the input integer
- *              size in Flags (often the current mode of the interpreter).
- *
- * Values for Flags:
- *      ACPI_STRTOUL_32BIT      - Max integer value is 32 bits
- *      ACPI_STRTOUL_64BIT      - Max integer value is 64 bits
- *      ACPI_STRTOUL_BASE16     - Input string is hexadecimal. Default
- *                                is 10/16 based on string prefix (0x).
+ *                                        returned. Must be a valid pointer
  *
- * NOTES:
- *   Negative numbers are not supported, as they are not supported by ACPI.
+ * RETURN:      Status and converted integer
+ *              Returns an exception on numeric overflow
  *
- *   Supports only base 16 or base 10 strings/values. Does not
- *   support Octal strings, as these are not supported by ACPI.
+ * DESCRIPTION: Convert a string into an unsigned integer. Performs either a
+ *              32-bit or 64-bit conversion, depending on the current global
+ *              integer width. Supports Decimal, Hex, and Octal strings.
  *
- * Current users of this support:
+ * Current users of this function:
  *
- *  interpreter - Implicit and explicit conversions, GPE method names
- *  debugger    - Command line input string conversion
- *  iASL        - Main parser, conversion of constants to integers
- *  iASL        - Data Table Compiler parser (constant math expressions)
  *  iASL        - Preprocessor (constant math expressions)
- *  acpi_dump   - Input table addresses
- *  acpi_exec   - Testing of the acpi_ut_strtoul64 function
- *
- * Note concerning callers:
- *   acpi_gbl_integer_byte_width can be used to set the 32/64 limit. If used,
- *   this global should be set to the proper width. For the core ACPICA code,
- *   this width depends on the DSDT version. For iASL, the default byte
- *   width is always 8 for the parser, but error checking is performed later
- *   to flag cases where a 64-bit constant is defined in a 32-bit DSDT/SSDT.
+ *  iASL        - Main parser, conversion of ASL constants to integers
+ *  iASL        - Data Table Compiler parser (constant math expressions)
  *
  ******************************************************************************/
-
-acpi_status acpi_ut_strtoul64(char *string, u32 flags, u64 *return_value)
+acpi_status acpi_ut_strtoul64(char *string, u64 *return_value)
 {
 	acpi_status status = AE_OK;
-	u32 base;
+	u32 base = 10;		/* Default is decimal */
 
 	ACPI_FUNCTION_TRACE_STR(ut_strtoul64, string);
 
-	/* Parameter validation */
-
-	if (!string || !return_value) {
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
-	}
-
 	*return_value = 0;
 
-	/* Check for zero-length string, returns 0 */
-
-	if (*string == 0) {
-		return_ACPI_STATUS(AE_OK);
-	}
-
-	/* Skip over any white space at start of string */
-
-	while (isspace((int)*string)) {
-		string++;
-	}
-
-	/* End of string? return 0 */
+	/* Null return string returns a value of zero */
 
 	if (*string == 0) {
 		return_ACPI_STATUS(AE_OK);
@@ -198,45 +121,45 @@ acpi_status acpi_ut_strtoul64(char *string, u32 flags, u64 *return_value)
 	/*
 	 * 1) The "0x" prefix indicates base 16. Per the ACPI specification,
 	 * the "0x" prefix is only allowed for implicit (non-strict) conversions.
-	 * However, we always allow it for compatibility with older ACPICA.
+	 * However, we always allow it for compatibility with older ACPICA and
+	 * just plain on principle.
 	 */
-	if ((*string == ACPI_ASCII_ZERO) &&
-	    (tolower((int)*(string + 1)) == 'x')) {
-		string += 2;	/* Go past the 0x */
-		if (*string == 0) {
-			return_ACPI_STATUS(AE_OK);	/* Return value 0 */
-		}
-
-		base = 16;
-	}
-
-	/* 2) Force to base 16 (implicit conversion case) */
-
-	else if (flags & ACPI_STRTOUL_BASE16) {
+	if (acpi_ut_detect_hex_prefix(&string)) {
 		base = 16;
 	}
 
-	/* 3) Default fallback is to Base 10 */
-
-	else {
-		base = 10;
+	/*
+	 * 2) Check for an octal constant, defined to be a leading zero
+	 * followed by an valid octal digit (0-7)
+	 */
+	else if (acpi_ut_detect_octal_prefix(&string)) {
+		base = 8;
 	}
 
-	/* Skip all leading zeros */
-
-	while (*string == ACPI_ASCII_ZERO) {
-		string++;
-		if (*string == 0) {
-			return_ACPI_STATUS(AE_OK);	/* Return value 0 */
-		}
+	if (!acpi_ut_remove_leading_zeros(&string)) {
+		return_ACPI_STATUS(AE_OK);	/* Return value 0 */
 	}
 
-	/* Perform the base 16 or 10 conversion */
-
-	if (base == 16) {
-		*return_value = acpi_ut_strtoul_base16(string, flags);
-	} else {
-		*return_value = acpi_ut_strtoul_base10(string, flags);
+	/*
+	 * Perform the base 8, 10, or 16 conversion. A numeric overflow will
+	 * return an exception.
+	 */
+	switch (base) {
+	case 8:
+		status = acpi_ut_convert_octal_string(string, return_value);
+		break;
+
+	case 10:
+		status = acpi_ut_convert_decimal_string(string, return_value);
+		break;
+
+	case 16:
+		status = acpi_ut_convert_hex_string(string, return_value);
+		break;
+
+	default:
+		status = AE_AML_INTERNAL;	/* Should never happen */
+		break;
 	}
 
 	return_ACPI_STATUS(status);
@@ -244,104 +167,167 @@ acpi_status acpi_ut_strtoul64(char *string, u32 flags, u64 *return_value)
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ut_strtoul_base10
+ * FUNCTION:    acpi_ut_implicit_strtoul64
+ *
+ * PARAMETERS:  string                  - Null terminated input string.
+ *                                        Must be a valid pointer
  *
- * PARAMETERS:  string                  - Null terminated input string
- *              flags                   - Conversion info
+ * RETURN:      Converted integer
  *
- * RETURN:      64-bit converted integer
+ * DESCRIPTION: Perform a 64-bit conversion with restrictions placed upon
+ *              an "implicit conversion" by the ACPI specification. Used by
+ *              many ASL operators that require an integer operand, and support
+ *              an automatic (implicit) conversion from a string operand
+ *              to the final integer operand. The restriction is that only
+ *              hex strings are supported.
  *
- * DESCRIPTION: Performs a base 10 conversion of the input string to an
- *              integer value, either 32 or 64 bits.
- *              Note: String must be valid and non-null.
+ * -----------------------------------------------------------------------------
+ *
+ * Base is always 16, either with or without the 0x prefix.
+ *
+ * Examples (both are hex values):
+ *      Add ("BA98", Arg0, Local0)
+ *      Subtract ("0x12345678", Arg1, Local1)
+ *
+ * Rules extracted from the ACPI specification:
+ *
+ *  The converted integer is initialized to the value zero.
+ *  The ASCII string is interpreted as a hexadecimal constant.
+ *
+ *  1)  A "0x" prefix is not allowed. However, ACPICA allows this as an
+ *      ACPI extension on general principle. (NO ERROR)
+ *
+ *  2)  Terminates when the size of an integer is reached (32 or 64 bits).
+ *      There are no numeric overflow conditions. (NO ERROR)
+ *
+ *  3)  The first non-hex character terminates the conversion and returns
+ *      the current accumulated value of the converted integer (NO ERROR).
+ *
+ *  4)  Conversion of a null (zero-length) string to an integer is
+ *      technically allowed. However, ACPICA allows as an ACPI extension.
+ *      The conversion returns the value 0. (NO ERROR)
+ *
+ * Note: there are no error conditions returned by this function. At
+ * the minimum, a value of zero is returned.
+ *
+ * Current users of this function:
+ *
+ *  interpreter - All runtime implicit conversions, as per ACPI specification
+ *  iASL        - Data Table Compiler parser (constant math expressions)
  *
  ******************************************************************************/
 
-static u64 acpi_ut_strtoul_base10(char *string, u32 flags)
+u64 acpi_ut_implicit_strtoul64(char *string)
 {
-	int ascii_digit;
-	u64 next_value;
-	u64 return_value = 0;
+	u64 converted_integer = 0;
 
-	/* Main loop: convert each ASCII byte in the input string */
+	ACPI_FUNCTION_TRACE_STR(ut_implicit_strtoul64, string);
 
-	while (*string) {
-		ascii_digit = *string;
-		if (!isdigit(ascii_digit)) {
-
-			/* Not ASCII 0-9, terminate */
-
-			goto exit;
-		}
-
-		/* Convert and insert (add) the decimal digit */
-
-		acpi_ut_short_multiply(return_value, 10, &next_value);
-		next_value += (ascii_digit - ACPI_ASCII_ZERO);
-
-		/* Check for overflow (32 or 64 bit) - return current converted value */
-
-		if (((flags & ACPI_STRTOUL_32BIT) && (next_value > ACPI_UINT32_MAX)) || (next_value < return_value)) {	/* 64-bit overflow case */
-			goto exit;
-		}
+	/*
+	 * Per the ACPI specification, only hexadecimal is supported for
+	 * implicit conversions, and the "0x" prefix is "not allowed".
+	 * However, allow a "0x" prefix as an ACPI extension.
+	 */
+	acpi_ut_detect_hex_prefix(&string);
 
-		return_value = next_value;
-		string++;
+	if (!acpi_ut_remove_leading_zeros(&string)) {
+		return_VALUE(0);
 	}
 
-exit:
-	return (return_value);
+	/*
+	 * Ignore overflow as per the ACPI specification. This is implemented by
+	 * ignoring the return status below. On overflow, the input string is
+	 * simply truncated.
+	 */
+	acpi_ut_convert_hex_string(string, &converted_integer);
+	return_VALUE(converted_integer);
 }
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ut_strtoul_base16
+ * FUNCTION:    acpi_ut_explicit_strtoul64
+ *
+ * PARAMETERS:  string                  - Null terminated input string.
+ *                                        Must be a valid pointer
+ *
+ * RETURN:      Converted integer
+ *
+ * DESCRIPTION: Perform a 64-bit conversion with the restrictions placed upon
+ *              an "explicit conversion" by the ACPI specification. The
+ *              main restriction is that only hex and decimal are supported.
+ *
+ * -----------------------------------------------------------------------------
+ *
+ * Base is either 10 (default) or 16 (with 0x prefix). There is no octal
+ * (base 8), as per the ACPI specification.
+ *
+ * Examples:
+ *      to_integer ("1000")     Decimal
+ *      to_integer ("0xABCD")   Hex
+ *
+ * Rules extracted from the ACPI specification:
+ *
+ *  1)  Thi input string is either a decimal or hexadecimal numeric string.
+ *      A hex value must be prefixed by "0x" or it is interpreted as decimal.
+ *
+ *  2)  The value must not exceed the maximum of an integer value
+ *      (32 or 64 bits). The ACPI specification states the behavior is
+ *      "unpredictable", so ACPICA matches the behavior of the implicit
+ *      conversion case. There are no numeric overflow conditions. (NO ERROR)
+ *
+ *  3)  Behavior on the first non-hex character is not specified by the ACPI
+ *      specification (for the to_integer operator), so ACPICA matches the
+ *      behavior of the implicit conversion case. It terminates the
+ *      conversion and returns the current accumulated value of the converted
+ *      integer. (NO ERROR)
  *
- * PARAMETERS:  string                  - Null terminated input string
- *              flags                   - conversion info
+ *  4)  Conversion of a null (zero-length) string to an integer is
+ *      technically allowed. However, ACPICA allows as an ACPI extension.
+ *      The conversion returns the value 0. (NO ERROR)
  *
- * RETURN:      64-bit converted integer
+ * Note: there are no error conditions returned by this function. At
+ * the minimum, a value of zero is returned.
  *
- * DESCRIPTION: Performs a base 16 conversion of the input string to an
- *              integer value, either 32 or 64 bits.
- *              Note: String must be valid and non-null.
+ * Current users of this function:
+ *
+ *  interpreter - Runtime ASL to_integer operator, as per the ACPI specification
  *
  ******************************************************************************/
 
-static u64 acpi_ut_strtoul_base16(char *string, u32 flags)
+u64 acpi_ut_explicit_strtoul64(char *string)
 {
-	int ascii_digit;
-	u32 valid_digits = 1;
-	u64 return_value = 0;
-
-	/* Main loop: convert each ASCII byte in the input string */
-
-	while (*string) {
-
-		/* Check for overflow (32 or 64 bit) - return current converted value */
-
-		if ((valid_digits > 16) ||
-		    ((valid_digits > 8) && (flags & ACPI_STRTOUL_32BIT))) {
-			goto exit;
-		}
-
-		ascii_digit = *string;
-		if (!isxdigit(ascii_digit)) {
-
-			/* Not Hex ASCII A-F, a-f, or 0-9, terminate */
+	u64 converted_integer = 0;
+	u32 base = 10;		/* Default is decimal */
 
-			goto exit;
-		}
+	ACPI_FUNCTION_TRACE_STR(ut_explicit_strtoul64, string);
 
-		/* Convert and insert the hex digit */
+	/*
+	 * Only Hex and Decimal are supported, as per the ACPI specification.
+	 * 0x prefix means hex; otherwise decimal is assumed.
+	 */
+	if (acpi_ut_detect_hex_prefix(&string)) {
+		base = 16;
+	}
 
-		acpi_ut_short_shift_left(return_value, 4, &return_value);
-		return_value |= acpi_ut_ascii_char_to_hex(ascii_digit);
+	if (!acpi_ut_remove_leading_zeros(&string)) {
+		return_VALUE(0);
+	}
 
-		string++;
-		valid_digits++;
+	/*
+	 * Ignore overflow as per the ACPI specification. This is implemented by
+	 * ignoring the return status below. On overflow, the input string is
+	 * simply truncated.
+	 */
+	switch (base) {
+	case 10:
+	default:
+		acpi_ut_convert_decimal_string(string, &converted_integer);
+		break;
+
+	case 16:
+		acpi_ut_convert_hex_string(string, &converted_integer);
+		break;
 	}
 
-exit:
-	return (return_value);
+	return_VALUE(converted_integer);
 }
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index ad54610ea6cd..17d61b1f2511 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -126,8 +126,12 @@ struct acpi_exception_info {
 #define AE_NOT_CONFIGURED               EXCEP_ENV (0x001C)
 #define AE_ACCESS                       EXCEP_ENV (0x001D)
 #define AE_IO_ERROR                     EXCEP_ENV (0x001E)
+#define AE_NUMERIC_OVERFLOW             EXCEP_ENV (0x001F)
+#define AE_HEX_OVERFLOW                 EXCEP_ENV (0x0020)
+#define AE_DECIMAL_OVERFLOW             EXCEP_ENV (0x0021)
+#define AE_OCTAL_OVERFLOW               EXCEP_ENV (0x0022)
 
-#define AE_CODE_ENV_MAX                 0x001E
+#define AE_CODE_ENV_MAX                 0x0022
 
 /*
  * Programmer exceptions
@@ -263,7 +267,15 @@ static const struct acpi_exception_info acpi_gbl_exception_names_env[] = {
 	EXCEP_TXT("AE_NOT_CONFIGURED",
 		  "The interface is not part of the current subsystem configuration"),
 	EXCEP_TXT("AE_ACCESS", "Permission denied for the requested operation"),
-	EXCEP_TXT("AE_IO_ERROR", "An I/O error occurred")
+	EXCEP_TXT("AE_IO_ERROR", "An I/O error occurred"),
+	EXCEP_TXT("AE_NUMERIC_OVERFLOW",
+		  "Overflow during string-to-integer conversion"),
+	EXCEP_TXT("AE_HEX_OVERFLOW",
+		  "Overflow during ASCII hex-to-binary conversion"),
+	EXCEP_TXT("AE_DECIMAL_OVERFLOW",
+		  "Overflow during ASCII decimal-to-binary conversion"),
+	EXCEP_TXT("AE_OCTAL_OVERFLOW",
+		  "Overflow during ASCII octal-to-binary conversion")
 };
 
 static const struct acpi_exception_info acpi_gbl_exception_names_pgm[] = {
diff --git a/tools/power/acpi/tools/acpidump/Makefile b/tools/power/acpi/tools/acpidump/Makefile
index f7c7af1f9258..b436f8675f6a 100644
--- a/tools/power/acpi/tools/acpidump/Makefile
+++ b/tools/power/acpi/tools/acpidump/Makefile
@@ -39,6 +39,7 @@ TOOL_OBJS = \
 	utnonansi.o\
 	utprint.o\
 	utstring.o\
+	utstrsuppt.o\
 	utstrtoul64.o\
 	utxferror.o\
 	oslinuxtbl.o\
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 60df1fbd4a77..0634449156d8 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -287,8 +287,7 @@ int ap_dump_table_by_address(char *ascii_address)
 
 	/* Convert argument to an integer physical address */
 
-	status = acpi_ut_strtoul64(ascii_address, ACPI_STRTOUL_64BIT,
-				   &long_address);
+	status = acpi_ut_strtoul64(ascii_address, &long_address);
 	if (ACPI_FAILURE(status)) {
 		fprintf(stderr, "%s: Could not convert to a physical address\n",
 			ascii_address);
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index 943b6b614683..22c3b4ee1617 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -208,9 +208,7 @@ static int ap_do_options(int argc, char **argv)
 		case 'r':	/* Dump tables from specified RSDP */
 
 			status =
-			    acpi_ut_strtoul64(acpi_gbl_optarg,
-					      ACPI_STRTOUL_64BIT,
-					      &gbl_rsdp_base);
+			    acpi_ut_strtoul64(acpi_gbl_optarg, &gbl_rsdp_base);
 			if (ACPI_FAILURE(status)) {
 				fprintf(stderr,
 					"%s: Could not convert to a physical address\n",
-- 
cgit v1.2.3


From c15562c0dcb2c7f26e891923b784cf1926b8c833 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Oct 2017 02:18:37 +0100
Subject: usbip: tools: Install all headers needed for libusbip development

usbip_host_driver.h now depends on several additional headers, which
need to be installed along with it.

Fixes: 021aed845303 ("staging: usbip: userspace: migrate usbip_host_driver ...")
Fixes: 3391ba0e2792 ("usbip: tools: Extract generic code to be shared with ...")
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Acked-by: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/usb/usbip/Makefile.am | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/usb/usbip/Makefile.am b/tools/usb/usbip/Makefile.am
index 66f8bf038c9f..45eaa70a71e0 100644
--- a/tools/usb/usbip/Makefile.am
+++ b/tools/usb/usbip/Makefile.am
@@ -1,6 +1,7 @@
 SUBDIRS := libsrc src
 includedir = @includedir@/usbip
 include_HEADERS := $(addprefix libsrc/, \
-		     usbip_common.h vhci_driver.h usbip_host_driver.h)
+		     usbip_common.h vhci_driver.h usbip_host_driver.h \
+		     list.h sysfs_utils.h usbip_host_common.h)
 
 dist_man_MANS := $(addprefix doc/, usbip.8 usbipd.8)
-- 
cgit v1.2.3


From e9b871ee098dfb91780e13bfc6e91e82c7b4ad73 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 4 Oct 2017 16:22:59 +0200
Subject: selftests: rtnetlink: try concurrent change of ifalias

to make sure this is serialized correctly.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 62c87da92770..e8c86c416ed0 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -278,6 +278,12 @@ kci_test_ifalias()
 	        ip link show "$devdummy" | grep -q "alias $namewant"
 		check_fail $?
 
+		for i in $(seq 1 100); do
+			uuidgen > "$syspathname" &
+		done
+
+		wait
+
 		# re-add the alias -- kernel should free mem when dummy dev is removed
 		ip link set dev "$devdummy" alias "$namewant"
 		check_err $?
-- 
cgit v1.2.3


From 390ee7e29fc8e6e90d3065b00afb047c4ee552f9 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Mon, 2 Oct 2017 22:50:23 -0700
Subject: bpf: enforce return code for cgroup-bpf programs

with addition of tnum logic the verifier got smart enough and
we can enforce return codes at program load time.
For now do so for cgroup-bpf program types.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       | 40 ++++++++++++++++
 tools/testing/selftests/bpf/test_verifier.c | 72 +++++++++++++++++++++++++++++
 2 files changed, 112 insertions(+)

(limited to 'tools')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4cf9b72c59a0..52b022310f6a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3073,6 +3073,43 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static int check_return_code(struct bpf_verifier_env *env)
+{
+	struct bpf_reg_state *reg;
+	struct tnum range = tnum_range(0, 1);
+
+	switch (env->prog->type) {
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_SOCK_OPS:
+		break;
+	default:
+		return 0;
+	}
+
+	reg = &env->cur_state.regs[BPF_REG_0];
+	if (reg->type != SCALAR_VALUE) {
+		verbose("At program exit the register R0 is not a known value (%s)\n",
+			reg_type_str[reg->type]);
+		return -EINVAL;
+	}
+
+	if (!tnum_in(range, reg->var_off)) {
+		verbose("At program exit the register R0 ");
+		if (!tnum_is_unknown(reg->var_off)) {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose("has value %s", tn_buf);
+		} else {
+			verbose("has unknown scalar value");
+		}
+		verbose(" should have been 0 or 1\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* non-recursive DFS pseudo code
  * 1  procedure DFS-iterative(G,v):
  * 2      label v as discovered
@@ -3863,6 +3900,9 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EACCES;
 				}
 
+				err = check_return_code(env);
+				if (err)
+					return err;
 process_bpf_exit:
 				insn_idx = pop_stack(env, &prev_insn_idx);
 				if (insn_idx < 0) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 290d5056c165..cc91d0159f43 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6892,6 +6892,78 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
+	{
+		"bpf_exit with invalid return code. test1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x0; 0xffffffff)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test3",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x0; 0x3)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x2; 0x0)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 is not a known value (ctx)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test7",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has unknown scalar value",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit v1.2.3


From 244d20efdb68c5c1a26c667baeb232ea163e2f69 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Mon, 2 Oct 2017 22:50:24 -0700
Subject: libbpf: introduce bpf_prog_detach2()

introduce bpf_prog_detach2() that takes one more argument prog_fd
vs bpf_prog_detach() that takes only attach_fd and type.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/lib/bpf/bpf.c | 12 ++++++++++++
 tools/lib/bpf/bpf.h |  1 +
 2 files changed, 13 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index daf624e4c720..d4b6ba8292ee 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -291,6 +291,18 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	 = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type = type;
+
+	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
+
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 118d00535a0d..afd64727c9cf 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -66,6 +66,7 @@ int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
 		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration);
-- 
cgit v1.2.3


From defd9c476fa6b01b4eb5450452bfd202138decb7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Mon, 2 Oct 2017 22:50:26 -0700
Subject: libbpf: sync bpf.h

tools/include/uapi/linux/bpf.h got out of sync with actual kernel header.
Update it.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/include/uapi/linux/bpf.h | 55 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 52 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6d2137b4cf38..cb2b9f95160a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -92,6 +92,7 @@ enum bpf_cmd {
 	BPF_PROG_GET_FD_BY_ID,
 	BPF_MAP_GET_FD_BY_ID,
 	BPF_OBJ_GET_INFO_BY_FD,
+	BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {
@@ -143,11 +144,47 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ *    cgrp2 (OVERRIDE prog C) ->
+ *      cgrp3 (MULTI prog D) ->
+ *        cgrp4 (OVERRIDE prog E) ->
+ *          cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+#define BPF_F_ALLOW_MULTI	(1U << 1)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -175,6 +212,9 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 #define BPF_OBJ_NAME_LEN 16U
 
 union bpf_attr {
@@ -253,6 +293,15 @@ union bpf_attr {
 		__u32		info_len;
 		__aligned_u64	info;
 	} info;
+
+	struct { /* anonymous struct used by BPF_PROG_QUERY command */
+		__u32		target_fd;	/* container object to query */
+		__u32		attach_type;
+		__u32		query_flags;
+		__u32		attach_flags;
+		__aligned_u64	prog_ids;
+		__u32		prog_cnt;
+	} query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
-- 
cgit v1.2.3


From 5d0cbf9b6c11964bf2f4041a5b0b6f81cb169736 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Mon, 2 Oct 2017 22:50:27 -0700
Subject: libbpf: add support for BPF_PROG_QUERY

add support for BPF_PROG_QUERY command to libbpf

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/lib/bpf/bpf.c | 20 ++++++++++++++++++++
 tools/lib/bpf/bpf.h |  3 ++-
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index d4b6ba8292ee..5128677e4117 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -303,6 +303,26 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
+{
+	union bpf_attr attr;
+	int ret;
+
+	bzero(&attr, sizeof(attr));
+	attr.query.target_fd	= target_fd;
+	attr.query.attach_type	= type;
+	attr.query.query_flags	= query_flags;
+	attr.query.prog_cnt	= *prog_cnt;
+	attr.query.prog_ids	= ptr_to_u64(prog_ids);
+
+	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+	if (attach_flags)
+		*attach_flags = attr.query.attach_flags;
+	*prog_cnt = attr.query.prog_cnt;
+	return ret;
+}
+
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index afd64727c9cf..6534889e2b2f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -75,5 +75,6 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 int bpf_prog_get_fd_by_id(__u32 id);
 int bpf_map_get_fd_by_id(__u32 id);
 int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
 #endif
-- 
cgit v1.2.3


From a92bb546cff0b31d96d5919ebfeda9c678756b42 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 4 Oct 2017 20:10:03 -0700
Subject: tools: rename tools/net directory to tools/bpf

We currently only have BPF tools in the tools/net directory.
We are about to add more BPF tools there, not necessarily
networking related, rename the directory and related Makefile
targets to bpf.

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                |    3 +-
 tools/Makefile             |   14 +-
 tools/bpf/Makefile         |   35 ++
 tools/bpf/bpf_asm.c        |   52 ++
 tools/bpf/bpf_dbg.c        | 1395 ++++++++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpf_exp.l        |  198 +++++++
 tools/bpf/bpf_exp.y        |  656 +++++++++++++++++++++
 tools/bpf/bpf_jit_disasm.c |  320 ++++++++++
 tools/net/Makefile         |   35 --
 tools/net/bpf_asm.c        |   52 --
 tools/net/bpf_dbg.c        | 1395 --------------------------------------------
 tools/net/bpf_exp.l        |  198 -------
 tools/net/bpf_exp.y        |  656 ---------------------
 tools/net/bpf_jit_disasm.c |  320 ----------
 14 files changed, 2664 insertions(+), 2665 deletions(-)
 create mode 100644 tools/bpf/Makefile
 create mode 100644 tools/bpf/bpf_asm.c
 create mode 100644 tools/bpf/bpf_dbg.c
 create mode 100644 tools/bpf/bpf_exp.l
 create mode 100644 tools/bpf/bpf_exp.y
 create mode 100644 tools/bpf/bpf_jit_disasm.c
 delete mode 100644 tools/net/Makefile
 delete mode 100644 tools/net/bpf_asm.c
 delete mode 100644 tools/net/bpf_dbg.c
 delete mode 100644 tools/net/bpf_exp.l
 delete mode 100644 tools/net/bpf_exp.y
 delete mode 100644 tools/net/bpf_jit_disasm.c

(limited to 'tools')

diff --git a/MAINTAINERS b/MAINTAINERS
index 5231392cf4bd..004816a585b8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2725,7 +2725,7 @@ F:	net/core/filter.c
 F:	net/sched/act_bpf.c
 F:	net/sched/cls_bpf.c
 F:	samples/bpf/
-F:	tools/net/bpf*
+F:	tools/bpf/
 F:	tools/testing/selftests/bpf/
 
 BROADCOM B44 10/100 ETHERNET DRIVER
@@ -9416,7 +9416,6 @@ F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
 F:	include/uapi/linux/net_namespace.h
-F:	tools/net/
 F:	tools/testing/selftests/net/
 F:	lib/random32.c
 
diff --git a/tools/Makefile b/tools/Makefile
index 9dfede37c8ff..df6fcb293fbc 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -19,7 +19,7 @@ help:
 	@echo '  kvm_stat               - top-like utility for displaying kvm statistics'
 	@echo '  leds                   - LEDs  tools'
 	@echo '  liblockdep             - user-space wrapper for kernel locking-validator'
-	@echo '  net                    - misc networking tools'
+	@echo '  bpf                    - misc BPF tools'
 	@echo '  perf                   - Linux performance measurement and analysis tool'
 	@echo '  selftests              - various kernel selftests'
 	@echo '  spi                    - spi tools'
@@ -57,7 +57,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds: FORCE
+cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds: FORCE
 	$(call descend,$@)
 
 liblockdep: FORCE
@@ -91,7 +91,7 @@ kvm_stat: FORCE
 
 all: acpi cgroup cpupower gpio hv firewire liblockdep \
 		perf selftests spi turbostat usb \
-		virtio vm net x86_energy_perf_policy \
+		virtio vm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat
 
 acpi_install:
@@ -100,7 +100,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install net_install objtool_install:
+cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install:
 	$(call descend,$(@:_install=),install)
 
 liblockdep_install:
@@ -124,7 +124,7 @@ kvm_stat_install:
 install: acpi_install cgroup_install cpupower_install gpio_install \
 		hv_install firewire_install iio_install liblockdep_install \
 		perf_install selftests_install turbostat_install usb_install \
-		virtio_install vm_install net_install x86_energy_perf_policy_install \
+		virtio_install vm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install
 
 acpi_clean:
@@ -133,7 +133,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean:
+cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean:
 	$(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -169,7 +169,7 @@ build_clean:
 
 clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
-		vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
+		vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
 		gpio_clean objtool_clean leds_clean
 
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
new file mode 100644
index 000000000000..ddf888010652
--- /dev/null
+++ b/tools/bpf/Makefile
@@ -0,0 +1,35 @@
+prefix = /usr
+
+CC = gcc
+LEX = flex
+YACC = bison
+
+CFLAGS += -Wall -O2
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
+%.yacc.c: %.y
+	$(YACC) -o $@ -d $<
+
+%.lex.c: %.l
+	$(LEX) -o $@ $<
+
+all : bpf_jit_disasm bpf_dbg bpf_asm
+
+bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
+bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
+bpf_jit_disasm : bpf_jit_disasm.o
+
+bpf_dbg : LDLIBS = -lreadline
+bpf_dbg : bpf_dbg.o
+
+bpf_asm : LDLIBS =
+bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
+bpf_exp.lex.o : bpf_exp.yacc.c
+
+clean :
+	rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
+
+install :
+	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
+	install bpf_dbg $(prefix)/bin/bpf_dbg
+	install bpf_asm $(prefix)/bin/bpf_asm
diff --git a/tools/bpf/bpf_asm.c b/tools/bpf/bpf_asm.c
new file mode 100644
index 000000000000..c15aef097b04
--- /dev/null
+++ b/tools/bpf/bpf_asm.c
@@ -0,0 +1,52 @@
+/*
+ * Minimal BPF assembler
+ *
+ * Instead of libpcap high-level filter expressions, it can be quite
+ * useful to define filters in low-level BPF assembler (that is kept
+ * close to Steven McCanne and Van Jacobson's original BPF paper).
+ * In particular for BPF JIT implementors, JIT security auditors, or
+ * just for defining BPF expressions that contain extensions which are
+ * not supported by compilers.
+ *
+ * How to get into it:
+ *
+ * 1) read Documentation/networking/filter.txt
+ * 2) Run `bpf_asm [-c] <filter-prog file>` to translate into binary
+ *    blob that is loadable with xt_bpf, cls_bpf et al. Note: -c will
+ *    pretty print a C-like construct.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+extern void bpf_asm_compile(FILE *fp, bool cstyle);
+
+int main(int argc, char **argv)
+{
+	FILE *fp = stdin;
+	bool cstyle = false;
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		if (!strncmp("-c", argv[i], 2)) {
+			cstyle = true;
+			continue;
+		}
+
+		fp = fopen(argv[i], "r");
+		if (!fp) {
+			fp = stdin;
+			continue;
+		}
+
+		break;
+	}
+
+	bpf_asm_compile(fp, cstyle);
+
+	return 0;
+}
diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c
new file mode 100644
index 000000000000..4f254bcc4423
--- /dev/null
+++ b/tools/bpf/bpf_dbg.c
@@ -0,0 +1,1395 @@
+/*
+ * Minimal BPF debugger
+ *
+ * Minimal BPF debugger that mimics the kernel's engine (w/o extensions)
+ * and allows for single stepping through selected packets from a pcap
+ * with a provided user filter in order to facilitate verification of a
+ * BPF program. Besides others, this is useful to verify BPF programs
+ * before attaching to a live system, and can be used in socket filters,
+ * cls_bpf, xt_bpf, team driver and e.g. PTP code; in particular when a
+ * single more complex BPF program is being used. Reasons for a more
+ * complex BPF program are likely primarily to optimize execution time
+ * for making a verdict when multiple simple BPF programs are combined
+ * into one in order to prevent parsing same headers multiple times.
+ *
+ * More on how to debug BPF opcodes see Documentation/networking/filter.txt
+ * which is the main document on BPF. Mini howto for getting started:
+ *
+ *  1) `./bpf_dbg` to enter the shell (shell cmds denoted with '>'):
+ *  2) > load bpf 6,40 0 0 12,21 0 3 20... (output from `bpf_asm` or
+ *     `tcpdump -iem1 -ddd port 22 | tr '\n' ','` to load as filter)
+ *  3) > load pcap foo.pcap
+ *  4) > run <n>/disassemble/dump/quit (self-explanatory)
+ *  5) > breakpoint 2 (sets bp at loaded BPF insns 2, do `run` then;
+ *       multiple bps can be set, of course, a call to `breakpoint`
+ *       w/o args shows currently loaded bps, `breakpoint reset` for
+ *       resetting all breakpoints)
+ *  6) > select 3 (`run` etc will start from the 3rd packet in the pcap)
+ *  7) > step [-<n>, +<n>] (performs single stepping through the BPF)
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <stdbool.h>
+#include <stdarg.h>
+#include <setjmp.h>
+#include <linux/filter.h>
+#include <linux/if_packet.h>
+#include <readline/readline.h>
+#include <readline/history.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <signal.h>
+#include <arpa/inet.h>
+#include <net/ethernet.h>
+
+#define TCPDUMP_MAGIC	0xa1b2c3d4
+
+#define BPF_LDX_B	(BPF_LDX | BPF_B)
+#define BPF_LDX_W	(BPF_LDX | BPF_W)
+#define BPF_JMP_JA	(BPF_JMP | BPF_JA)
+#define BPF_JMP_JEQ	(BPF_JMP | BPF_JEQ)
+#define BPF_JMP_JGT	(BPF_JMP | BPF_JGT)
+#define BPF_JMP_JGE	(BPF_JMP | BPF_JGE)
+#define BPF_JMP_JSET	(BPF_JMP | BPF_JSET)
+#define BPF_ALU_ADD	(BPF_ALU | BPF_ADD)
+#define BPF_ALU_SUB	(BPF_ALU | BPF_SUB)
+#define BPF_ALU_MUL	(BPF_ALU | BPF_MUL)
+#define BPF_ALU_DIV	(BPF_ALU | BPF_DIV)
+#define BPF_ALU_MOD	(BPF_ALU | BPF_MOD)
+#define BPF_ALU_NEG	(BPF_ALU | BPF_NEG)
+#define BPF_ALU_AND	(BPF_ALU | BPF_AND)
+#define BPF_ALU_OR	(BPF_ALU | BPF_OR)
+#define BPF_ALU_XOR	(BPF_ALU | BPF_XOR)
+#define BPF_ALU_LSH	(BPF_ALU | BPF_LSH)
+#define BPF_ALU_RSH	(BPF_ALU | BPF_RSH)
+#define BPF_MISC_TAX	(BPF_MISC | BPF_TAX)
+#define BPF_MISC_TXA	(BPF_MISC | BPF_TXA)
+#define BPF_LD_B	(BPF_LD | BPF_B)
+#define BPF_LD_H	(BPF_LD | BPF_H)
+#define BPF_LD_W	(BPF_LD | BPF_W)
+
+#ifndef array_size
+# define array_size(x)	(sizeof(x) / sizeof((x)[0]))
+#endif
+
+#ifndef __check_format_printf
+# define __check_format_printf(pos_fmtstr, pos_fmtargs) \
+	__attribute__ ((format (printf, (pos_fmtstr), (pos_fmtargs))))
+#endif
+
+enum {
+	CMD_OK,
+	CMD_ERR,
+	CMD_EX,
+};
+
+struct shell_cmd {
+	const char *name;
+	int (*func)(char *args);
+};
+
+struct pcap_filehdr {
+	uint32_t magic;
+	uint16_t version_major;
+	uint16_t version_minor;
+	int32_t  thiszone;
+	uint32_t sigfigs;
+	uint32_t snaplen;
+	uint32_t linktype;
+};
+
+struct pcap_timeval {
+	int32_t tv_sec;
+	int32_t tv_usec;
+};
+
+struct pcap_pkthdr {
+	struct pcap_timeval ts;
+	uint32_t caplen;
+	uint32_t len;
+};
+
+struct bpf_regs {
+	uint32_t A;
+	uint32_t X;
+	uint32_t M[BPF_MEMWORDS];
+	uint32_t R;
+	bool     Rs;
+	uint16_t Pc;
+};
+
+static struct sock_filter bpf_image[BPF_MAXINSNS + 1];
+static unsigned int bpf_prog_len;
+
+static int bpf_breakpoints[64];
+static struct bpf_regs bpf_regs[BPF_MAXINSNS + 1];
+static struct bpf_regs bpf_curr;
+static unsigned int bpf_regs_len;
+
+static int pcap_fd = -1;
+static unsigned int pcap_packet;
+static size_t pcap_map_size;
+static char *pcap_ptr_va_start, *pcap_ptr_va_curr;
+
+static const char * const op_table[] = {
+	[BPF_ST]	= "st",
+	[BPF_STX]	= "stx",
+	[BPF_LD_B]	= "ldb",
+	[BPF_LD_H]	= "ldh",
+	[BPF_LD_W]	= "ld",
+	[BPF_LDX]	= "ldx",
+	[BPF_LDX_B]	= "ldxb",
+	[BPF_JMP_JA]	= "ja",
+	[BPF_JMP_JEQ]	= "jeq",
+	[BPF_JMP_JGT]	= "jgt",
+	[BPF_JMP_JGE]	= "jge",
+	[BPF_JMP_JSET]	= "jset",
+	[BPF_ALU_ADD]	= "add",
+	[BPF_ALU_SUB]	= "sub",
+	[BPF_ALU_MUL]	= "mul",
+	[BPF_ALU_DIV]	= "div",
+	[BPF_ALU_MOD]	= "mod",
+	[BPF_ALU_NEG]	= "neg",
+	[BPF_ALU_AND]	= "and",
+	[BPF_ALU_OR]	= "or",
+	[BPF_ALU_XOR]	= "xor",
+	[BPF_ALU_LSH]	= "lsh",
+	[BPF_ALU_RSH]	= "rsh",
+	[BPF_MISC_TAX]	= "tax",
+	[BPF_MISC_TXA]	= "txa",
+	[BPF_RET]	= "ret",
+};
+
+static __check_format_printf(1, 2) int rl_printf(const char *fmt, ...)
+{
+	int ret;
+	va_list vl;
+
+	va_start(vl, fmt);
+	ret = vfprintf(rl_outstream, fmt, vl);
+	va_end(vl);
+
+	return ret;
+}
+
+static int matches(const char *cmd, const char *pattern)
+{
+	int len = strlen(cmd);
+
+	if (len > strlen(pattern))
+		return -1;
+
+	return memcmp(pattern, cmd, len);
+}
+
+static void hex_dump(const uint8_t *buf, size_t len)
+{
+	int i;
+
+	rl_printf("%3u: ", 0);
+	for (i = 0; i < len; i++) {
+		if (i && !(i % 16))
+			rl_printf("\n%3u: ", i);
+		rl_printf("%02x ", buf[i]);
+	}
+	rl_printf("\n");
+}
+
+static bool bpf_prog_loaded(void)
+{
+	if (bpf_prog_len == 0)
+		rl_printf("no bpf program loaded!\n");
+
+	return bpf_prog_len > 0;
+}
+
+static void bpf_disasm(const struct sock_filter f, unsigned int i)
+{
+	const char *op, *fmt;
+	int val = f.k;
+	char buf[256];
+
+	switch (f.code) {
+	case BPF_RET | BPF_K:
+		op = op_table[BPF_RET];
+		fmt = "#%#x";
+		break;
+	case BPF_RET | BPF_A:
+		op = op_table[BPF_RET];
+		fmt = "a";
+		break;
+	case BPF_RET | BPF_X:
+		op = op_table[BPF_RET];
+		fmt = "x";
+		break;
+	case BPF_MISC_TAX:
+		op = op_table[BPF_MISC_TAX];
+		fmt = "";
+		break;
+	case BPF_MISC_TXA:
+		op = op_table[BPF_MISC_TXA];
+		fmt = "";
+		break;
+	case BPF_ST:
+		op = op_table[BPF_ST];
+		fmt = "M[%d]";
+		break;
+	case BPF_STX:
+		op = op_table[BPF_STX];
+		fmt = "M[%d]";
+		break;
+	case BPF_LD_W | BPF_ABS:
+		op = op_table[BPF_LD_W];
+		fmt = "[%d]";
+		break;
+	case BPF_LD_H | BPF_ABS:
+		op = op_table[BPF_LD_H];
+		fmt = "[%d]";
+		break;
+	case BPF_LD_B | BPF_ABS:
+		op = op_table[BPF_LD_B];
+		fmt = "[%d]";
+		break;
+	case BPF_LD_W | BPF_LEN:
+		op = op_table[BPF_LD_W];
+		fmt = "#len";
+		break;
+	case BPF_LD_W | BPF_IND:
+		op = op_table[BPF_LD_W];
+		fmt = "[x+%d]";
+		break;
+	case BPF_LD_H | BPF_IND:
+		op = op_table[BPF_LD_H];
+		fmt = "[x+%d]";
+		break;
+	case BPF_LD_B | BPF_IND:
+		op = op_table[BPF_LD_B];
+		fmt = "[x+%d]";
+		break;
+	case BPF_LD | BPF_IMM:
+		op = op_table[BPF_LD_W];
+		fmt = "#%#x";
+		break;
+	case BPF_LDX | BPF_IMM:
+		op = op_table[BPF_LDX];
+		fmt = "#%#x";
+		break;
+	case BPF_LDX_B | BPF_MSH:
+		op = op_table[BPF_LDX_B];
+		fmt = "4*([%d]&0xf)";
+		break;
+	case BPF_LD | BPF_MEM:
+		op = op_table[BPF_LD_W];
+		fmt = "M[%d]";
+		break;
+	case BPF_LDX | BPF_MEM:
+		op = op_table[BPF_LDX];
+		fmt = "M[%d]";
+		break;
+	case BPF_JMP_JA:
+		op = op_table[BPF_JMP_JA];
+		fmt = "%d";
+		val = i + 1 + f.k;
+		break;
+	case BPF_JMP_JGT | BPF_X:
+		op = op_table[BPF_JMP_JGT];
+		fmt = "x";
+		break;
+	case BPF_JMP_JGT | BPF_K:
+		op = op_table[BPF_JMP_JGT];
+		fmt = "#%#x";
+		break;
+	case BPF_JMP_JGE | BPF_X:
+		op = op_table[BPF_JMP_JGE];
+		fmt = "x";
+		break;
+	case BPF_JMP_JGE | BPF_K:
+		op = op_table[BPF_JMP_JGE];
+		fmt = "#%#x";
+		break;
+	case BPF_JMP_JEQ | BPF_X:
+		op = op_table[BPF_JMP_JEQ];
+		fmt = "x";
+		break;
+	case BPF_JMP_JEQ | BPF_K:
+		op = op_table[BPF_JMP_JEQ];
+		fmt = "#%#x";
+		break;
+	case BPF_JMP_JSET | BPF_X:
+		op = op_table[BPF_JMP_JSET];
+		fmt = "x";
+		break;
+	case BPF_JMP_JSET | BPF_K:
+		op = op_table[BPF_JMP_JSET];
+		fmt = "#%#x";
+		break;
+	case BPF_ALU_NEG:
+		op = op_table[BPF_ALU_NEG];
+		fmt = "";
+		break;
+	case BPF_ALU_LSH | BPF_X:
+		op = op_table[BPF_ALU_LSH];
+		fmt = "x";
+		break;
+	case BPF_ALU_LSH | BPF_K:
+		op = op_table[BPF_ALU_LSH];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_RSH | BPF_X:
+		op = op_table[BPF_ALU_RSH];
+		fmt = "x";
+		break;
+	case BPF_ALU_RSH | BPF_K:
+		op = op_table[BPF_ALU_RSH];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_ADD | BPF_X:
+		op = op_table[BPF_ALU_ADD];
+		fmt = "x";
+		break;
+	case BPF_ALU_ADD | BPF_K:
+		op = op_table[BPF_ALU_ADD];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_SUB | BPF_X:
+		op = op_table[BPF_ALU_SUB];
+		fmt = "x";
+		break;
+	case BPF_ALU_SUB | BPF_K:
+		op = op_table[BPF_ALU_SUB];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_MUL | BPF_X:
+		op = op_table[BPF_ALU_MUL];
+		fmt = "x";
+		break;
+	case BPF_ALU_MUL | BPF_K:
+		op = op_table[BPF_ALU_MUL];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_DIV | BPF_X:
+		op = op_table[BPF_ALU_DIV];
+		fmt = "x";
+		break;
+	case BPF_ALU_DIV | BPF_K:
+		op = op_table[BPF_ALU_DIV];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_MOD | BPF_X:
+		op = op_table[BPF_ALU_MOD];
+		fmt = "x";
+		break;
+	case BPF_ALU_MOD | BPF_K:
+		op = op_table[BPF_ALU_MOD];
+		fmt = "#%d";
+		break;
+	case BPF_ALU_AND | BPF_X:
+		op = op_table[BPF_ALU_AND];
+		fmt = "x";
+		break;
+	case BPF_ALU_AND | BPF_K:
+		op = op_table[BPF_ALU_AND];
+		fmt = "#%#x";
+		break;
+	case BPF_ALU_OR | BPF_X:
+		op = op_table[BPF_ALU_OR];
+		fmt = "x";
+		break;
+	case BPF_ALU_OR | BPF_K:
+		op = op_table[BPF_ALU_OR];
+		fmt = "#%#x";
+		break;
+	case BPF_ALU_XOR | BPF_X:
+		op = op_table[BPF_ALU_XOR];
+		fmt = "x";
+		break;
+	case BPF_ALU_XOR | BPF_K:
+		op = op_table[BPF_ALU_XOR];
+		fmt = "#%#x";
+		break;
+	default:
+		op = "nosup";
+		fmt = "%#x";
+		val = f.code;
+		break;
+	}
+
+	memset(buf, 0, sizeof(buf));
+	snprintf(buf, sizeof(buf), fmt, val);
+	buf[sizeof(buf) - 1] = 0;
+
+	if ((BPF_CLASS(f.code) == BPF_JMP && BPF_OP(f.code) != BPF_JA))
+		rl_printf("l%d:\t%s %s, l%d, l%d\n", i, op, buf,
+			  i + 1 + f.jt, i + 1 + f.jf);
+	else
+		rl_printf("l%d:\t%s %s\n", i, op, buf);
+}
+
+static void bpf_dump_curr(struct bpf_regs *r, struct sock_filter *f)
+{
+	int i, m = 0;
+
+	rl_printf("pc:       [%u]\n", r->Pc);
+	rl_printf("code:     [%u] jt[%u] jf[%u] k[%u]\n",
+		  f->code, f->jt, f->jf, f->k);
+	rl_printf("curr:     ");
+	bpf_disasm(*f, r->Pc);
+
+	if (f->jt || f->jf) {
+		rl_printf("jt:       ");
+		bpf_disasm(*(f + f->jt + 1), r->Pc + f->jt + 1);
+		rl_printf("jf:       ");
+		bpf_disasm(*(f + f->jf + 1), r->Pc + f->jf + 1);
+	}
+
+	rl_printf("A:        [%#08x][%u]\n", r->A, r->A);
+	rl_printf("X:        [%#08x][%u]\n", r->X, r->X);
+	if (r->Rs)
+		rl_printf("ret:      [%#08x][%u]!\n", r->R, r->R);
+
+	for (i = 0; i < BPF_MEMWORDS; i++) {
+		if (r->M[i]) {
+			m++;
+			rl_printf("M[%d]: [%#08x][%u]\n", i, r->M[i], r->M[i]);
+		}
+	}
+	if (m == 0)
+		rl_printf("M[0,%d]:  [%#08x][%u]\n", BPF_MEMWORDS - 1, 0, 0);
+}
+
+static void bpf_dump_pkt(uint8_t *pkt, uint32_t pkt_caplen, uint32_t pkt_len)
+{
+	if (pkt_caplen != pkt_len)
+		rl_printf("cap: %u, len: %u\n", pkt_caplen, pkt_len);
+	else
+		rl_printf("len: %u\n", pkt_len);
+
+	hex_dump(pkt, pkt_caplen);
+}
+
+static void bpf_disasm_all(const struct sock_filter *f, unsigned int len)
+{
+	unsigned int i;
+
+	for (i = 0; i < len; i++)
+		bpf_disasm(f[i], i);
+}
+
+static void bpf_dump_all(const struct sock_filter *f, unsigned int len)
+{
+	unsigned int i;
+
+	rl_printf("/* { op, jt, jf, k }, */\n");
+	for (i = 0; i < len; i++)
+		rl_printf("{ %#04x, %2u, %2u, %#010x },\n",
+			  f[i].code, f[i].jt, f[i].jf, f[i].k);
+}
+
+static bool bpf_runnable(struct sock_filter *f, unsigned int len)
+{
+	int sock, ret, i;
+	struct sock_fprog bpf = {
+		.filter = f,
+		.len = len,
+	};
+
+	sock = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sock < 0) {
+		rl_printf("cannot open socket!\n");
+		return false;
+	}
+	ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf));
+	close(sock);
+	if (ret < 0) {
+		rl_printf("program not allowed to run by kernel!\n");
+		return false;
+	}
+	for (i = 0; i < len; i++) {
+		if (BPF_CLASS(f[i].code) == BPF_LD &&
+		    f[i].k > SKF_AD_OFF) {
+			rl_printf("extensions currently not supported!\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void bpf_reset_breakpoints(void)
+{
+	int i;
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++)
+		bpf_breakpoints[i] = -1;
+}
+
+static void bpf_set_breakpoints(unsigned int where)
+{
+	int i;
+	bool set = false;
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++) {
+		if (bpf_breakpoints[i] == (int) where) {
+			rl_printf("breakpoint already set!\n");
+			set = true;
+			break;
+		}
+
+		if (bpf_breakpoints[i] == -1 && set == false) {
+			bpf_breakpoints[i] = where;
+			set = true;
+		}
+	}
+
+	if (!set)
+		rl_printf("too many breakpoints set, reset first!\n");
+}
+
+static void bpf_dump_breakpoints(void)
+{
+	int i;
+
+	rl_printf("breakpoints: ");
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++) {
+		if (bpf_breakpoints[i] < 0)
+			continue;
+		rl_printf("%d ", bpf_breakpoints[i]);
+	}
+
+	rl_printf("\n");
+}
+
+static void bpf_reset(void)
+{
+	bpf_regs_len = 0;
+
+	memset(bpf_regs, 0, sizeof(bpf_regs));
+	memset(&bpf_curr, 0, sizeof(bpf_curr));
+}
+
+static void bpf_safe_regs(void)
+{
+	memcpy(&bpf_regs[bpf_regs_len++], &bpf_curr, sizeof(bpf_curr));
+}
+
+static bool bpf_restore_regs(int off)
+{
+	unsigned int index = bpf_regs_len - 1 + off;
+
+	if (index == 0) {
+		bpf_reset();
+		return true;
+	} else if (index < bpf_regs_len) {
+		memcpy(&bpf_curr, &bpf_regs[index], sizeof(bpf_curr));
+		bpf_regs_len = index;
+		return true;
+	} else {
+		rl_printf("reached bottom of register history stack!\n");
+		return false;
+	}
+}
+
+static uint32_t extract_u32(uint8_t *pkt, uint32_t off)
+{
+	uint32_t r;
+
+	memcpy(&r, &pkt[off], sizeof(r));
+
+	return ntohl(r);
+}
+
+static uint16_t extract_u16(uint8_t *pkt, uint32_t off)
+{
+	uint16_t r;
+
+	memcpy(&r, &pkt[off], sizeof(r));
+
+	return ntohs(r);
+}
+
+static uint8_t extract_u8(uint8_t *pkt, uint32_t off)
+{
+	return pkt[off];
+}
+
+static void set_return(struct bpf_regs *r)
+{
+	r->R = 0;
+	r->Rs = true;
+}
+
+static void bpf_single_step(struct bpf_regs *r, struct sock_filter *f,
+			    uint8_t *pkt, uint32_t pkt_caplen,
+			    uint32_t pkt_len)
+{
+	uint32_t K = f->k;
+	int d;
+
+	switch (f->code) {
+	case BPF_RET | BPF_K:
+		r->R = K;
+		r->Rs = true;
+		break;
+	case BPF_RET | BPF_A:
+		r->R = r->A;
+		r->Rs = true;
+		break;
+	case BPF_RET | BPF_X:
+		r->R = r->X;
+		r->Rs = true;
+		break;
+	case BPF_MISC_TAX:
+		r->X = r->A;
+		break;
+	case BPF_MISC_TXA:
+		r->A = r->X;
+		break;
+	case BPF_ST:
+		r->M[K] = r->A;
+		break;
+	case BPF_STX:
+		r->M[K] = r->X;
+		break;
+	case BPF_LD_W | BPF_ABS:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint32_t))
+			r->A = extract_u32(pkt, K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_H | BPF_ABS:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint16_t))
+			r->A = extract_u16(pkt, K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_B | BPF_ABS:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint8_t))
+			r->A = extract_u8(pkt, K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_W | BPF_IND:
+		d = pkt_caplen - (r->X + K);
+		if (d >= sizeof(uint32_t))
+			r->A = extract_u32(pkt, r->X + K);
+		break;
+	case BPF_LD_H | BPF_IND:
+		d = pkt_caplen - (r->X + K);
+		if (d >= sizeof(uint16_t))
+			r->A = extract_u16(pkt, r->X + K);
+		else
+			set_return(r);
+		break;
+	case BPF_LD_B | BPF_IND:
+		d = pkt_caplen - (r->X + K);
+		if (d >= sizeof(uint8_t))
+			r->A = extract_u8(pkt, r->X + K);
+		else
+			set_return(r);
+		break;
+	case BPF_LDX_B | BPF_MSH:
+		d = pkt_caplen - K;
+		if (d >= sizeof(uint8_t)) {
+			r->X = extract_u8(pkt, K);
+			r->X = (r->X & 0xf) << 2;
+		} else
+			set_return(r);
+		break;
+	case BPF_LD_W | BPF_LEN:
+		r->A = pkt_len;
+		break;
+	case BPF_LDX_W | BPF_LEN:
+		r->A = pkt_len;
+		break;
+	case BPF_LD | BPF_IMM:
+		r->A = K;
+		break;
+	case BPF_LDX | BPF_IMM:
+		r->X = K;
+		break;
+	case BPF_LD | BPF_MEM:
+		r->A = r->M[K];
+		break;
+	case BPF_LDX | BPF_MEM:
+		r->X = r->M[K];
+		break;
+	case BPF_JMP_JA:
+		r->Pc += K;
+		break;
+	case BPF_JMP_JGT | BPF_X:
+		r->Pc += r->A > r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JGT | BPF_K:
+		r->Pc += r->A > K ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JGE | BPF_X:
+		r->Pc += r->A >= r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JGE | BPF_K:
+		r->Pc += r->A >= K ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JEQ | BPF_X:
+		r->Pc += r->A == r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JEQ | BPF_K:
+		r->Pc += r->A == K ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JSET | BPF_X:
+		r->Pc += r->A & r->X ? f->jt : f->jf;
+		break;
+	case BPF_JMP_JSET | BPF_K:
+		r->Pc += r->A & K ? f->jt : f->jf;
+		break;
+	case BPF_ALU_NEG:
+		r->A = -r->A;
+		break;
+	case BPF_ALU_LSH | BPF_X:
+		r->A <<= r->X;
+		break;
+	case BPF_ALU_LSH | BPF_K:
+		r->A <<= K;
+		break;
+	case BPF_ALU_RSH | BPF_X:
+		r->A >>= r->X;
+		break;
+	case BPF_ALU_RSH | BPF_K:
+		r->A >>= K;
+		break;
+	case BPF_ALU_ADD | BPF_X:
+		r->A += r->X;
+		break;
+	case BPF_ALU_ADD | BPF_K:
+		r->A += K;
+		break;
+	case BPF_ALU_SUB | BPF_X:
+		r->A -= r->X;
+		break;
+	case BPF_ALU_SUB | BPF_K:
+		r->A -= K;
+		break;
+	case BPF_ALU_MUL | BPF_X:
+		r->A *= r->X;
+		break;
+	case BPF_ALU_MUL | BPF_K:
+		r->A *= K;
+		break;
+	case BPF_ALU_DIV | BPF_X:
+	case BPF_ALU_MOD | BPF_X:
+		if (r->X == 0) {
+			set_return(r);
+			break;
+		}
+		goto do_div;
+	case BPF_ALU_DIV | BPF_K:
+	case BPF_ALU_MOD | BPF_K:
+		if (K == 0) {
+			set_return(r);
+			break;
+		}
+do_div:
+		switch (f->code) {
+		case BPF_ALU_DIV | BPF_X:
+			r->A /= r->X;
+			break;
+		case BPF_ALU_DIV | BPF_K:
+			r->A /= K;
+			break;
+		case BPF_ALU_MOD | BPF_X:
+			r->A %= r->X;
+			break;
+		case BPF_ALU_MOD | BPF_K:
+			r->A %= K;
+			break;
+		}
+		break;
+	case BPF_ALU_AND | BPF_X:
+		r->A &= r->X;
+		break;
+	case BPF_ALU_AND | BPF_K:
+		r->A &= K;
+		break;
+	case BPF_ALU_OR | BPF_X:
+		r->A |= r->X;
+		break;
+	case BPF_ALU_OR | BPF_K:
+		r->A |= K;
+		break;
+	case BPF_ALU_XOR | BPF_X:
+		r->A ^= r->X;
+		break;
+	case BPF_ALU_XOR | BPF_K:
+		r->A ^= K;
+		break;
+	}
+}
+
+static bool bpf_pc_has_breakpoint(uint16_t pc)
+{
+	int i;
+
+	for (i = 0; i < array_size(bpf_breakpoints); i++) {
+		if (bpf_breakpoints[i] < 0)
+			continue;
+		if (bpf_breakpoints[i] == pc)
+			return true;
+	}
+
+	return false;
+}
+
+static bool bpf_handle_breakpoint(struct bpf_regs *r, struct sock_filter *f,
+				  uint8_t *pkt, uint32_t pkt_caplen,
+				  uint32_t pkt_len)
+{
+	rl_printf("-- register dump --\n");
+	bpf_dump_curr(r, &f[r->Pc]);
+	rl_printf("-- packet dump --\n");
+	bpf_dump_pkt(pkt, pkt_caplen, pkt_len);
+	rl_printf("(breakpoint)\n");
+	return true;
+}
+
+static int bpf_run_all(struct sock_filter *f, uint16_t bpf_len, uint8_t *pkt,
+		       uint32_t pkt_caplen, uint32_t pkt_len)
+{
+	bool stop = false;
+
+	while (bpf_curr.Rs == false && stop == false) {
+		bpf_safe_regs();
+
+		if (bpf_pc_has_breakpoint(bpf_curr.Pc))
+			stop = bpf_handle_breakpoint(&bpf_curr, f, pkt,
+						     pkt_caplen, pkt_len);
+
+		bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen,
+				pkt_len);
+		bpf_curr.Pc++;
+	}
+
+	return stop ? -1 : bpf_curr.R;
+}
+
+static int bpf_run_stepping(struct sock_filter *f, uint16_t bpf_len,
+			    uint8_t *pkt, uint32_t pkt_caplen,
+			    uint32_t pkt_len, int next)
+{
+	bool stop = false;
+	int i = 1;
+
+	while (bpf_curr.Rs == false && stop == false) {
+		bpf_safe_regs();
+
+		if (i++ == next)
+			stop = bpf_handle_breakpoint(&bpf_curr, f, pkt,
+						     pkt_caplen, pkt_len);
+
+		bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen,
+				pkt_len);
+		bpf_curr.Pc++;
+	}
+
+	return stop ? -1 : bpf_curr.R;
+}
+
+static bool pcap_loaded(void)
+{
+	if (pcap_fd < 0)
+		rl_printf("no pcap file loaded!\n");
+
+	return pcap_fd >= 0;
+}
+
+static struct pcap_pkthdr *pcap_curr_pkt(void)
+{
+	return (void *) pcap_ptr_va_curr;
+}
+
+static bool pcap_next_pkt(void)
+{
+	struct pcap_pkthdr *hdr = pcap_curr_pkt();
+
+	if (pcap_ptr_va_curr + sizeof(*hdr) -
+	    pcap_ptr_va_start >= pcap_map_size)
+		return false;
+	if (hdr->caplen == 0 || hdr->len == 0 || hdr->caplen > hdr->len)
+		return false;
+	if (pcap_ptr_va_curr + sizeof(*hdr) + hdr->caplen -
+	    pcap_ptr_va_start >= pcap_map_size)
+		return false;
+
+	pcap_ptr_va_curr += (sizeof(*hdr) + hdr->caplen);
+	return true;
+}
+
+static void pcap_reset_pkt(void)
+{
+	pcap_ptr_va_curr = pcap_ptr_va_start + sizeof(struct pcap_filehdr);
+}
+
+static int try_load_pcap(const char *file)
+{
+	struct pcap_filehdr *hdr;
+	struct stat sb;
+	int ret;
+
+	pcap_fd = open(file, O_RDONLY);
+	if (pcap_fd < 0) {
+		rl_printf("cannot open pcap [%s]!\n", strerror(errno));
+		return CMD_ERR;
+	}
+
+	ret = fstat(pcap_fd, &sb);
+	if (ret < 0) {
+		rl_printf("cannot fstat pcap file!\n");
+		return CMD_ERR;
+	}
+
+	if (!S_ISREG(sb.st_mode)) {
+		rl_printf("not a regular pcap file, duh!\n");
+		return CMD_ERR;
+	}
+
+	pcap_map_size = sb.st_size;
+	if (pcap_map_size <= sizeof(struct pcap_filehdr)) {
+		rl_printf("pcap file too small!\n");
+		return CMD_ERR;
+	}
+
+	pcap_ptr_va_start = mmap(NULL, pcap_map_size, PROT_READ,
+				 MAP_SHARED | MAP_LOCKED, pcap_fd, 0);
+	if (pcap_ptr_va_start == MAP_FAILED) {
+		rl_printf("mmap of file failed!");
+		return CMD_ERR;
+	}
+
+	hdr = (void *) pcap_ptr_va_start;
+	if (hdr->magic != TCPDUMP_MAGIC) {
+		rl_printf("wrong pcap magic!\n");
+		return CMD_ERR;
+	}
+
+	pcap_reset_pkt();
+
+	return CMD_OK;
+
+}
+
+static void try_close_pcap(void)
+{
+	if (pcap_fd >= 0) {
+		munmap(pcap_ptr_va_start, pcap_map_size);
+		close(pcap_fd);
+
+		pcap_ptr_va_start = pcap_ptr_va_curr = NULL;
+		pcap_map_size = 0;
+		pcap_packet = 0;
+		pcap_fd = -1;
+	}
+}
+
+static int cmd_load_bpf(char *bpf_string)
+{
+	char sp, *token, separator = ',';
+	unsigned short bpf_len, i = 0;
+	struct sock_filter tmp;
+
+	bpf_prog_len = 0;
+	memset(bpf_image, 0, sizeof(bpf_image));
+
+	if (sscanf(bpf_string, "%hu%c", &bpf_len, &sp) != 2 ||
+	    sp != separator || bpf_len > BPF_MAXINSNS || bpf_len == 0) {
+		rl_printf("syntax error in head length encoding!\n");
+		return CMD_ERR;
+	}
+
+	token = bpf_string;
+	while ((token = strchr(token, separator)) && (++token)[0]) {
+		if (i >= bpf_len) {
+			rl_printf("program exceeds encoded length!\n");
+			return CMD_ERR;
+		}
+
+		if (sscanf(token, "%hu %hhu %hhu %u,",
+			   &tmp.code, &tmp.jt, &tmp.jf, &tmp.k) != 4) {
+			rl_printf("syntax error at instruction %d!\n", i);
+			return CMD_ERR;
+		}
+
+		bpf_image[i].code = tmp.code;
+		bpf_image[i].jt = tmp.jt;
+		bpf_image[i].jf = tmp.jf;
+		bpf_image[i].k = tmp.k;
+
+		i++;
+	}
+
+	if (i != bpf_len) {
+		rl_printf("syntax error exceeding encoded length!\n");
+		return CMD_ERR;
+	} else
+		bpf_prog_len = bpf_len;
+	if (!bpf_runnable(bpf_image, bpf_prog_len))
+		bpf_prog_len = 0;
+
+	return CMD_OK;
+}
+
+static int cmd_load_pcap(char *file)
+{
+	char *file_trim, *tmp;
+
+	file_trim = strtok_r(file, " ", &tmp);
+	if (file_trim == NULL)
+		return CMD_ERR;
+
+	try_close_pcap();
+
+	return try_load_pcap(file_trim);
+}
+
+static int cmd_load(char *arg)
+{
+	char *subcmd, *cont, *tmp = strdup(arg);
+	int ret = CMD_OK;
+
+	subcmd = strtok_r(tmp, " ", &cont);
+	if (subcmd == NULL)
+		goto out;
+	if (matches(subcmd, "bpf") == 0) {
+		bpf_reset();
+		bpf_reset_breakpoints();
+
+		ret = cmd_load_bpf(cont);
+	} else if (matches(subcmd, "pcap") == 0) {
+		ret = cmd_load_pcap(cont);
+	} else {
+out:
+		rl_printf("bpf <code>:  load bpf code\n");
+		rl_printf("pcap <file>: load pcap file\n");
+		ret = CMD_ERR;
+	}
+
+	free(tmp);
+	return ret;
+}
+
+static int cmd_step(char *num)
+{
+	struct pcap_pkthdr *hdr;
+	int steps, ret;
+
+	if (!bpf_prog_loaded() || !pcap_loaded())
+		return CMD_ERR;
+
+	steps = strtol(num, NULL, 10);
+	if (steps == 0 || strlen(num) == 0)
+		steps = 1;
+	if (steps < 0) {
+		if (!bpf_restore_regs(steps))
+			return CMD_ERR;
+		steps = 1;
+	}
+
+	hdr = pcap_curr_pkt();
+	ret = bpf_run_stepping(bpf_image, bpf_prog_len,
+			       (uint8_t *) hdr + sizeof(*hdr),
+			       hdr->caplen, hdr->len, steps);
+	if (ret >= 0 || bpf_curr.Rs) {
+		bpf_reset();
+		if (!pcap_next_pkt()) {
+			rl_printf("(going back to first packet)\n");
+			pcap_reset_pkt();
+		} else {
+			rl_printf("(next packet)\n");
+		}
+	}
+
+	return CMD_OK;
+}
+
+static int cmd_select(char *num)
+{
+	unsigned int which, i;
+	bool have_next = true;
+
+	if (!pcap_loaded() || strlen(num) == 0)
+		return CMD_ERR;
+
+	which = strtoul(num, NULL, 10);
+	if (which == 0) {
+		rl_printf("packet count starts with 1, clamping!\n");
+		which = 1;
+	}
+
+	pcap_reset_pkt();
+	bpf_reset();
+
+	for (i = 0; i < which && (have_next = pcap_next_pkt()); i++)
+		/* noop */;
+	if (!have_next || pcap_curr_pkt() == NULL) {
+		rl_printf("no packet #%u available!\n", which);
+		pcap_reset_pkt();
+		return CMD_ERR;
+	}
+
+	return CMD_OK;
+}
+
+static int cmd_breakpoint(char *subcmd)
+{
+	if (!bpf_prog_loaded())
+		return CMD_ERR;
+	if (strlen(subcmd) == 0)
+		bpf_dump_breakpoints();
+	else if (matches(subcmd, "reset") == 0)
+		bpf_reset_breakpoints();
+	else {
+		unsigned int where = strtoul(subcmd, NULL, 10);
+
+		if (where < bpf_prog_len) {
+			bpf_set_breakpoints(where);
+			rl_printf("breakpoint at: ");
+			bpf_disasm(bpf_image[where], where);
+		}
+	}
+
+	return CMD_OK;
+}
+
+static int cmd_run(char *num)
+{
+	static uint32_t pass, fail;
+	bool has_limit = true;
+	int pkts = 0, i = 0;
+
+	if (!bpf_prog_loaded() || !pcap_loaded())
+		return CMD_ERR;
+
+	pkts = strtol(num, NULL, 10);
+	if (pkts == 0 || strlen(num) == 0)
+		has_limit = false;
+
+	do {
+		struct pcap_pkthdr *hdr = pcap_curr_pkt();
+		int ret = bpf_run_all(bpf_image, bpf_prog_len,
+				      (uint8_t *) hdr + sizeof(*hdr),
+				      hdr->caplen, hdr->len);
+		if (ret > 0)
+			pass++;
+		else if (ret == 0)
+			fail++;
+		else
+			return CMD_OK;
+		bpf_reset();
+	} while (pcap_next_pkt() && (!has_limit || (has_limit && ++i < pkts)));
+
+	rl_printf("bpf passes:%u fails:%u\n", pass, fail);
+
+	pcap_reset_pkt();
+	bpf_reset();
+
+	pass = fail = 0;
+	return CMD_OK;
+}
+
+static int cmd_disassemble(char *line_string)
+{
+	bool single_line = false;
+	unsigned long line;
+
+	if (!bpf_prog_loaded())
+		return CMD_ERR;
+	if (strlen(line_string) > 0 &&
+	    (line = strtoul(line_string, NULL, 10)) < bpf_prog_len)
+		single_line = true;
+	if (single_line)
+		bpf_disasm(bpf_image[line], line);
+	else
+		bpf_disasm_all(bpf_image, bpf_prog_len);
+
+	return CMD_OK;
+}
+
+static int cmd_dump(char *dontcare)
+{
+	if (!bpf_prog_loaded())
+		return CMD_ERR;
+
+	bpf_dump_all(bpf_image, bpf_prog_len);
+
+	return CMD_OK;
+}
+
+static int cmd_quit(char *dontcare)
+{
+	return CMD_EX;
+}
+
+static const struct shell_cmd cmds[] = {
+	{ .name = "load", .func = cmd_load },
+	{ .name = "select", .func = cmd_select },
+	{ .name = "step", .func = cmd_step },
+	{ .name = "run", .func = cmd_run },
+	{ .name = "breakpoint", .func = cmd_breakpoint },
+	{ .name = "disassemble", .func = cmd_disassemble },
+	{ .name = "dump", .func = cmd_dump },
+	{ .name = "quit", .func = cmd_quit },
+};
+
+static int execf(char *arg)
+{
+	char *cmd, *cont, *tmp = strdup(arg);
+	int i, ret = 0, len;
+
+	cmd = strtok_r(tmp, " ", &cont);
+	if (cmd == NULL)
+		goto out;
+	len = strlen(cmd);
+	for (i = 0; i < array_size(cmds); i++) {
+		if (len != strlen(cmds[i].name))
+			continue;
+		if (strncmp(cmds[i].name, cmd, len) == 0) {
+			ret = cmds[i].func(cont);
+			break;
+		}
+	}
+out:
+	free(tmp);
+	return ret;
+}
+
+static char *shell_comp_gen(const char *buf, int state)
+{
+	static int list_index, len;
+
+	if (!state) {
+		list_index = 0;
+		len = strlen(buf);
+	}
+
+	for (; list_index < array_size(cmds); ) {
+		const char *name = cmds[list_index].name;
+
+		list_index++;
+		if (strncmp(name, buf, len) == 0)
+			return strdup(name);
+	}
+
+	return NULL;
+}
+
+static char **shell_completion(const char *buf, int start, int end)
+{
+	char **matches = NULL;
+
+	if (start == 0)
+		matches = rl_completion_matches(buf, shell_comp_gen);
+
+	return matches;
+}
+
+static void intr_shell(int sig)
+{
+	if (rl_end)
+		rl_kill_line(-1, 0);
+
+	rl_crlf();
+	rl_refresh_line(0, 0);
+	rl_free_line_state();
+}
+
+static void init_shell(FILE *fin, FILE *fout)
+{
+	char file[128];
+
+	snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME"));
+	read_history(file);
+
+	rl_instream = fin;
+	rl_outstream = fout;
+
+	rl_readline_name = "bpf_dbg";
+	rl_terminal_name = getenv("TERM");
+
+	rl_catch_signals = 0;
+	rl_catch_sigwinch = 1;
+
+	rl_attempted_completion_function = shell_completion;
+
+	rl_bind_key('\t', rl_complete);
+
+	rl_bind_key_in_map('\t', rl_complete, emacs_meta_keymap);
+	rl_bind_key_in_map('\033', rl_complete, emacs_meta_keymap);
+
+	snprintf(file, sizeof(file), "%s/.bpf_dbg_init", getenv("HOME"));
+	rl_read_init_file(file);
+
+	rl_prep_terminal(0);
+	rl_set_signals();
+
+	signal(SIGINT, intr_shell);
+}
+
+static void exit_shell(FILE *fin, FILE *fout)
+{
+	char file[128];
+
+	snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME"));
+	write_history(file);
+
+	clear_history();
+	rl_deprep_terminal();
+
+	try_close_pcap();
+
+	if (fin != stdin)
+		fclose(fin);
+	if (fout != stdout)
+		fclose(fout);
+}
+
+static int run_shell_loop(FILE *fin, FILE *fout)
+{
+	char *buf;
+
+	init_shell(fin, fout);
+
+	while ((buf = readline("> ")) != NULL) {
+		int ret = execf(buf);
+		if (ret == CMD_EX)
+			break;
+		if (ret == CMD_OK && strlen(buf) > 0)
+			add_history(buf);
+
+		free(buf);
+	}
+
+	exit_shell(fin, fout);
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	FILE *fin = NULL, *fout = NULL;
+
+	if (argc >= 2)
+		fin = fopen(argv[1], "r");
+	if (argc >= 3)
+		fout = fopen(argv[2], "w");
+
+	return run_shell_loop(fin ? : stdin, fout ? : stdout);
+}
diff --git a/tools/bpf/bpf_exp.l b/tools/bpf/bpf_exp.l
new file mode 100644
index 000000000000..bd83149e7be0
--- /dev/null
+++ b/tools/bpf/bpf_exp.l
@@ -0,0 +1,198 @@
+/*
+ * BPF asm code lexer
+ *
+ * This program is free software; you can distribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * Syntax kept close to:
+ *
+ * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+ * architecture for user-level packet capture. In Proceedings of the
+ * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+ * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+ * CA, USA, 2-2.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+%{
+
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <linux/filter.h>
+
+#include "bpf_exp.yacc.h"
+
+extern void yyerror(const char *str);
+
+%}
+
+%option align
+%option ecs
+
+%option nounput
+%option noreject
+%option noinput
+%option noyywrap
+
+%option 8bit
+%option caseless
+%option yylineno
+
+%%
+
+"ldb"		{ return OP_LDB; }
+"ldh"		{ return OP_LDH; }
+"ld"		{ return OP_LD; }
+"ldi"		{ return OP_LDI; }
+"ldx"		{ return OP_LDX; }
+"ldxi"		{ return OP_LDXI; }
+"ldxb"		{ return OP_LDXB; }
+"st"		{ return OP_ST; }
+"stx"		{ return OP_STX; }
+"jmp"		{ return OP_JMP; }
+"ja"		{ return OP_JMP; }
+"jeq"		{ return OP_JEQ; }
+"jneq"		{ return OP_JNEQ; }
+"jne"		{ return OP_JNEQ; }
+"jlt"		{ return OP_JLT; }
+"jle"		{ return OP_JLE; }
+"jgt"		{ return OP_JGT; }
+"jge"		{ return OP_JGE; }
+"jset"		{ return OP_JSET; }
+"add"		{ return OP_ADD; }
+"sub"		{ return OP_SUB; }
+"mul"		{ return OP_MUL; }
+"div"		{ return OP_DIV; }
+"mod"		{ return OP_MOD; }
+"neg"		{ return OP_NEG; }
+"and"		{ return OP_AND; }
+"xor"		{ return OP_XOR; }
+"or"		{ return OP_OR; }
+"lsh"		{ return OP_LSH; }
+"rsh"		{ return OP_RSH; }
+"ret"		{ return OP_RET; }
+"tax"		{ return OP_TAX; }
+"txa"		{ return OP_TXA; }
+
+"#"?("len")	{ return K_PKT_LEN; }
+
+"#"?("proto")	{
+		yylval.number = SKF_AD_PROTOCOL;
+		return extension;
+	}
+"#"?("type")	{
+		yylval.number = SKF_AD_PKTTYPE;
+		return extension;
+	}
+"#"?("poff")	{
+		yylval.number = SKF_AD_PAY_OFFSET;
+		return extension;
+	}
+"#"?("ifidx")	{
+		yylval.number = SKF_AD_IFINDEX;
+		return extension;
+	}
+"#"?("nla")	{
+		yylval.number = SKF_AD_NLATTR;
+		return extension;
+	}
+"#"?("nlan")	{
+		yylval.number = SKF_AD_NLATTR_NEST;
+		return extension;
+	}
+"#"?("mark")	{
+		yylval.number = SKF_AD_MARK;
+		return extension;
+	}
+"#"?("queue")	{
+		yylval.number = SKF_AD_QUEUE;
+		return extension;
+	}
+"#"?("hatype")	{
+		yylval.number = SKF_AD_HATYPE;
+		return extension;
+	}
+"#"?("rxhash")	{
+		yylval.number = SKF_AD_RXHASH;
+		return extension;
+	}
+"#"?("cpu")	{
+		yylval.number = SKF_AD_CPU;
+		return extension;
+	}
+"#"?("vlan_tci") {
+		yylval.number = SKF_AD_VLAN_TAG;
+		return extension;
+	}
+"#"?("vlan_pr")	{
+		yylval.number = SKF_AD_VLAN_TAG_PRESENT;
+		return extension;
+	}
+"#"?("vlan_avail") {
+		yylval.number = SKF_AD_VLAN_TAG_PRESENT;
+		return extension;
+	}
+"#"?("vlan_tpid") {
+		yylval.number = SKF_AD_VLAN_TPID;
+		return extension;
+	}
+"#"?("rand")	{
+		yylval.number = SKF_AD_RANDOM;
+		return extension;
+	}
+
+":"		{ return ':'; }
+","		{ return ','; }
+"#"		{ return '#'; }
+"%"		{ return '%'; }
+"["		{ return '['; }
+"]"		{ return ']'; }
+"("		{ return '('; }
+")"		{ return ')'; }
+"x"		{ return 'x'; }
+"a"		{ return 'a'; }
+"+"		{ return '+'; }
+"M"		{ return 'M'; }
+"*"		{ return '*'; }
+"&"		{ return '&'; }
+
+([0][x][a-fA-F0-9]+) {
+			yylval.number = strtoul(yytext, NULL, 16);
+			return number;
+		}
+([0][b][0-1]+)	{
+			yylval.number = strtol(yytext + 2, NULL, 2);
+			return number;
+		}
+(([0])|([-+]?[1-9][0-9]*)) {
+			yylval.number = strtol(yytext, NULL, 10);
+			return number;
+		}
+([0][0-9]+)	{
+			yylval.number = strtol(yytext + 1, NULL, 8);
+			return number;
+		}
+[a-zA-Z_][a-zA-Z0-9_]+ {
+			yylval.label = strdup(yytext);
+			return label;
+		}
+
+"/*"([^\*]|\*[^/])*"*/"		{ /* NOP */ }
+";"[^\n]*			{ /* NOP */ }
+^#.*				{ /* NOP */ }
+[ \t]+				{ /* NOP */ }
+[ \n]+				{ /* NOP */ }
+
+.		{
+			printf("unknown character \'%s\'", yytext);
+			yyerror("lex unknown character");
+		}
+
+%%
diff --git a/tools/bpf/bpf_exp.y b/tools/bpf/bpf_exp.y
new file mode 100644
index 000000000000..56ba1de50784
--- /dev/null
+++ b/tools/bpf/bpf_exp.y
@@ -0,0 +1,656 @@
+/*
+ * BPF asm code parser
+ *
+ * This program is free software; you can distribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * Syntax kept close to:
+ *
+ * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+ * architecture for user-level packet capture. In Proceedings of the
+ * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+ * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+ * CA, USA, 2-2.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+%{
+
+#include <stdio.h>
+#include <string.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <errno.h>
+#include <assert.h>
+#include <linux/filter.h>
+
+#include "bpf_exp.yacc.h"
+
+enum jmp_type { JTL, JFL, JKL };
+
+extern FILE *yyin;
+extern int yylineno;
+extern int yylex(void);
+extern void yyerror(const char *str);
+
+extern void bpf_asm_compile(FILE *fp, bool cstyle);
+static void bpf_set_curr_instr(uint16_t op, uint8_t jt, uint8_t jf, uint32_t k);
+static void bpf_set_curr_label(char *label);
+static void bpf_set_jmp_label(char *label, enum jmp_type type);
+
+%}
+
+%union {
+	char *label;
+	uint32_t number;
+}
+
+%token OP_LDB OP_LDH OP_LD OP_LDX OP_ST OP_STX OP_JMP OP_JEQ OP_JGT OP_JGE
+%token OP_JSET OP_ADD OP_SUB OP_MUL OP_DIV OP_AND OP_OR OP_XOR OP_LSH OP_RSH
+%token OP_RET OP_TAX OP_TXA OP_LDXB OP_MOD OP_NEG OP_JNEQ OP_JLT OP_JLE OP_LDI
+%token OP_LDXI
+
+%token K_PKT_LEN
+
+%token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%'
+
+%token extension number label
+
+%type <label> label
+%type <number> extension
+%type <number> number
+
+%%
+
+prog
+	: line
+	| prog line
+	;
+
+line
+	: instr
+	| labelled_instr
+	;
+
+labelled_instr
+	: labelled instr
+	;
+
+instr
+	: ldb
+	| ldh
+	| ld
+	| ldi
+	| ldx
+	| ldxi
+	| st
+	| stx
+	| jmp
+	| jeq
+	| jneq
+	| jlt
+	| jle
+	| jgt
+	| jge
+	| jset
+	| add
+	| sub
+	| mul
+	| div
+	| mod
+	| neg
+	| and
+	| or
+	| xor
+	| lsh
+	| rsh
+	| ret
+	| tax
+	| txa
+	;
+
+labelled
+	: label ':' { bpf_set_curr_label($1); }
+	;
+
+ldb
+	: OP_LDB '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $5); }
+	| OP_LDB '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $6); }
+	| OP_LDB '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, $3); }
+	| OP_LDB extension {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + $2); }
+	;
+
+ldh
+	: OP_LDH '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $5); }
+	| OP_LDH '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $6); }
+	| OP_LDH '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, $3); }
+	| OP_LDH extension {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + $2); }
+	;
+
+ldi
+	: OP_LDI '#' number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
+	| OP_LDI number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $2); }
+	;
+
+ld
+	: OP_LD '#' number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
+	| OP_LD K_PKT_LEN {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_LEN, 0, 0, 0); }
+	| OP_LD extension {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + $2); }
+	| OP_LD 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); }
+	| OP_LD '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $5); }
+	| OP_LD '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $6); }
+	| OP_LD '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, $3); }
+	;
+
+ldxi
+	: OP_LDXI '#' number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
+	| OP_LDXI number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $2); }
+	;
+
+ldx
+	: OP_LDX '#' number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
+	| OP_LDX K_PKT_LEN {
+		bpf_set_curr_instr(BPF_LDX | BPF_W | BPF_LEN, 0, 0, 0); }
+	| OP_LDX 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_LDX | BPF_MEM, 0, 0, $4); }
+	| OP_LDXB number '*' '(' '[' number ']' '&' number ')' {
+		if ($2 != 4 || $9 != 0xf) {
+			fprintf(stderr, "ldxb offset not supported!\n");
+			exit(0);
+		} else {
+			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
+	| OP_LDX number '*' '(' '[' number ']' '&' number ')' {
+		if ($2 != 4 || $9 != 0xf) {
+			fprintf(stderr, "ldxb offset not supported!\n");
+			exit(0);
+		} else {
+			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
+	;
+
+st
+	: OP_ST 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_ST, 0, 0, $4); }
+	;
+
+stx
+	: OP_STX 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_STX, 0, 0, $4); }
+	;
+
+jmp
+	: OP_JMP label {
+		bpf_set_jmp_label($2, JKL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JA, 0, 0, 0); }
+	;
+
+jeq
+	: OP_JEQ '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JEQ 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JEQ 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	;
+
+jneq
+	: OP_JNEQ '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JNEQ 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JNEQ '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	;
+
+jlt
+	: OP_JLT '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JLT 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JLT '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	;
+
+jle
+	: OP_JLE '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JLE 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JLE '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	;
+
+jgt
+	: OP_JGT '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JGT 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JGT 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	;
+
+jge
+	: OP_JGE '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JGE 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JGE 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	;
+
+jset
+	: OP_JSET '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
+	| OP_JSET 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
+	| OP_JSET 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	;
+
+add
+	: OP_ADD '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_K, 0, 0, $3); }
+	| OP_ADD 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
+	| OP_ADD '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
+	;
+
+sub
+	: OP_SUB '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_K, 0, 0, $3); }
+	| OP_SUB 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
+	| OP_SUB '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
+	;
+
+mul
+	: OP_MUL '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_K, 0, 0, $3); }
+	| OP_MUL 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
+	| OP_MUL '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
+	;
+
+div
+	: OP_DIV '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_K, 0, 0, $3); }
+	| OP_DIV 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
+	| OP_DIV '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
+	;
+
+mod
+	: OP_MOD '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_K, 0, 0, $3); }
+	| OP_MOD 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
+	| OP_MOD '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
+	;
+
+neg
+	: OP_NEG {
+		bpf_set_curr_instr(BPF_ALU | BPF_NEG, 0, 0, 0); }
+	;
+
+and
+	: OP_AND '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_K, 0, 0, $3); }
+	| OP_AND 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
+	| OP_AND '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
+	;
+
+or
+	: OP_OR '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_K, 0, 0, $3); }
+	| OP_OR 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
+	| OP_OR '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
+	;
+
+xor
+	: OP_XOR '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_K, 0, 0, $3); }
+	| OP_XOR 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
+	| OP_XOR '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
+	;
+
+lsh
+	: OP_LSH '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_K, 0, 0, $3); }
+	| OP_LSH 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
+	| OP_LSH '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
+	;
+
+rsh
+	: OP_RSH '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_K, 0, 0, $3); }
+	| OP_RSH 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
+	| OP_RSH '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
+	;
+
+ret
+	: OP_RET 'a' {
+		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
+	| OP_RET '%' 'a' {
+		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
+	| OP_RET 'x' {
+		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
+	| OP_RET '%' 'x' {
+		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
+	| OP_RET '#' number {
+		bpf_set_curr_instr(BPF_RET | BPF_K, 0, 0, $3); }
+	;
+
+tax
+	: OP_TAX {
+		bpf_set_curr_instr(BPF_MISC | BPF_TAX, 0, 0, 0); }
+	;
+
+txa
+	: OP_TXA {
+		bpf_set_curr_instr(BPF_MISC | BPF_TXA, 0, 0, 0); }
+	;
+
+%%
+
+static int curr_instr = 0;
+static struct sock_filter out[BPF_MAXINSNS];
+static char **labels, **labels_jt, **labels_jf, **labels_k;
+
+static void bpf_assert_max(void)
+{
+	if (curr_instr >= BPF_MAXINSNS) {
+		fprintf(stderr, "only max %u insns allowed!\n", BPF_MAXINSNS);
+		exit(0);
+	}
+}
+
+static void bpf_set_curr_instr(uint16_t code, uint8_t jt, uint8_t jf,
+			       uint32_t k)
+{
+	bpf_assert_max();
+	out[curr_instr].code = code;
+	out[curr_instr].jt = jt;
+	out[curr_instr].jf = jf;
+	out[curr_instr].k = k;
+	curr_instr++;
+}
+
+static void bpf_set_curr_label(char *label)
+{
+	bpf_assert_max();
+	labels[curr_instr] = label;
+}
+
+static void bpf_set_jmp_label(char *label, enum jmp_type type)
+{
+	bpf_assert_max();
+	switch (type) {
+	case JTL:
+		labels_jt[curr_instr] = label;
+		break;
+	case JFL:
+		labels_jf[curr_instr] = label;
+		break;
+	case JKL:
+		labels_k[curr_instr] = label;
+		break;
+	}
+}
+
+static int bpf_find_insns_offset(const char *label)
+{
+	int i, max = curr_instr, ret = -ENOENT;
+
+	for (i = 0; i < max; i++) {
+		if (labels[i] && !strcmp(label, labels[i])) {
+			ret = i;
+			break;
+		}
+	}
+
+	if (ret == -ENOENT) {
+		fprintf(stderr, "no such label \'%s\'!\n", label);
+		exit(0);
+	}
+
+	return ret;
+}
+
+static void bpf_stage_1_insert_insns(void)
+{
+	yyparse();
+}
+
+static void bpf_reduce_k_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_k[i]) {
+			int off = bpf_find_insns_offset(labels_k[i]);
+			out[i].k = (uint32_t) (off - i - 1);
+		}
+	}
+}
+
+static void bpf_reduce_jt_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_jt[i]) {
+			int off = bpf_find_insns_offset(labels_jt[i]);
+			out[i].jt = (uint8_t) (off - i -1);
+		}
+	}
+}
+
+static void bpf_reduce_jf_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_jf[i]) {
+			int off = bpf_find_insns_offset(labels_jf[i]);
+			out[i].jf = (uint8_t) (off - i - 1);
+		}
+	}
+}
+
+static void bpf_stage_2_reduce_labels(void)
+{
+	bpf_reduce_k_jumps();
+	bpf_reduce_jt_jumps();
+	bpf_reduce_jf_jumps();
+}
+
+static void bpf_pretty_print_c(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++)
+		printf("{ %#04x, %2u, %2u, %#010x },\n", out[i].code,
+		       out[i].jt, out[i].jf, out[i].k);
+}
+
+static void bpf_pretty_print(void)
+{
+	int i;
+
+	printf("%u,", curr_instr);
+	for (i = 0; i < curr_instr; i++)
+		printf("%u %u %u %u,", out[i].code,
+		       out[i].jt, out[i].jf, out[i].k);
+	printf("\n");
+}
+
+static void bpf_init(void)
+{
+	memset(out, 0, sizeof(out));
+
+	labels = calloc(BPF_MAXINSNS, sizeof(*labels));
+	assert(labels);
+	labels_jt = calloc(BPF_MAXINSNS, sizeof(*labels_jt));
+	assert(labels_jt);
+	labels_jf = calloc(BPF_MAXINSNS, sizeof(*labels_jf));
+	assert(labels_jf);
+	labels_k = calloc(BPF_MAXINSNS, sizeof(*labels_k));
+	assert(labels_k);
+}
+
+static void bpf_destroy_labels(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		free(labels_jf[i]);
+		free(labels_jt[i]);
+		free(labels_k[i]);
+		free(labels[i]);
+	}
+}
+
+static void bpf_destroy(void)
+{
+	bpf_destroy_labels();
+	free(labels_jt);
+	free(labels_jf);
+	free(labels_k);
+	free(labels);
+}
+
+void bpf_asm_compile(FILE *fp, bool cstyle)
+{
+	yyin = fp;
+
+	bpf_init();
+	bpf_stage_1_insert_insns();
+	bpf_stage_2_reduce_labels();
+	bpf_destroy();
+
+	if (cstyle)
+		bpf_pretty_print_c();
+	else
+		bpf_pretty_print();
+
+	if (fp != stdin)
+		fclose(yyin);
+}
+
+void yyerror(const char *str)
+{
+	fprintf(stderr, "error: %s at line %d\n", str, yylineno);
+	exit(1);
+}
diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c
new file mode 100644
index 000000000000..422d9abd666a
--- /dev/null
+++ b/tools/bpf/bpf_jit_disasm.c
@@ -0,0 +1,320 @@
+/*
+ * Minimal BPF JIT image disassembler
+ *
+ * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for
+ * debugging or verification purposes.
+ *
+ * To get the disassembly of the JIT code, do the following:
+ *
+ *  1) `echo 2 > /proc/sys/net/core/bpf_jit_enable`
+ *  2) Load a BPF filter (e.g. `tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24`)
+ *  3) Run e.g. `bpf_jit_disasm -o` to read out the last JIT code
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+#include <bfd.h>
+#include <dis-asm.h>
+#include <regex.h>
+#include <fcntl.h>
+#include <sys/klog.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#define CMD_ACTION_SIZE_BUFFER		10
+#define CMD_ACTION_READ_ALL		3
+
+static void get_exec_path(char *tpath, size_t size)
+{
+	char *path;
+	ssize_t len;
+
+	snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
+	tpath[size - 1] = 0;
+
+	path = strdup(tpath);
+	assert(path);
+
+	len = readlink(path, tpath, size);
+	tpath[len] = 0;
+
+	free(path);
+}
+
+static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
+{
+	int count, i, pc = 0;
+	char tpath[256];
+	struct disassemble_info info;
+	disassembler_ftype disassemble;
+	bfd *bfdf;
+
+	memset(tpath, 0, sizeof(tpath));
+	get_exec_path(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	assert(bfdf);
+	assert(bfd_check_format(bfdf, bfd_object));
+
+	init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf);
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+	info.buffer = image;
+	info.buffer_length = len;
+
+	disassemble_init_for_target(&info);
+
+	disassemble = disassembler(bfdf);
+	assert(disassemble);
+
+	do {
+		printf("%4x:\t", pc);
+
+		count = disassemble(pc, &info);
+
+		if (opcodes) {
+			printf("\n\t");
+			for (i = 0; i < count; ++i)
+				printf("%02x ", (uint8_t) image[pc + i]);
+		}
+		printf("\n");
+
+		pc += count;
+	} while(count > 0 && pc < len);
+
+	bfd_close(bfdf);
+}
+
+static char *get_klog_buff(unsigned int *klen)
+{
+	int ret, len;
+	char *buff;
+
+	len = klogctl(CMD_ACTION_SIZE_BUFFER, NULL, 0);
+	if (len < 0)
+		return NULL;
+
+	buff = malloc(len);
+	if (!buff)
+		return NULL;
+
+	ret = klogctl(CMD_ACTION_READ_ALL, buff, len);
+	if (ret < 0) {
+		free(buff);
+		return NULL;
+	}
+
+	*klen = ret;
+	return buff;
+}
+
+static char *get_flog_buff(const char *file, unsigned int *klen)
+{
+	int fd, ret, len;
+	struct stat fi;
+	char *buff;
+
+	fd = open(file, O_RDONLY);
+	if (fd < 0)
+		return NULL;
+
+	ret = fstat(fd, &fi);
+	if (ret < 0 || !S_ISREG(fi.st_mode))
+		goto out;
+
+	len = fi.st_size + 1;
+	buff = malloc(len);
+	if (!buff)
+		goto out;
+
+	memset(buff, 0, len);
+	ret = read(fd, buff, len - 1);
+	if (ret <= 0)
+		goto out_free;
+
+	close(fd);
+	*klen = ret;
+	return buff;
+out_free:
+	free(buff);
+out:
+	close(fd);
+	return NULL;
+}
+
+static char *get_log_buff(const char *file, unsigned int *klen)
+{
+	return file ? get_flog_buff(file, klen) : get_klog_buff(klen);
+}
+
+static void put_log_buff(char *buff)
+{
+	free(buff);
+}
+
+static uint8_t *get_last_jit_image(char *haystack, size_t hlen,
+				   unsigned int *ilen)
+{
+	char *ptr, *pptr, *tmp;
+	off_t off = 0;
+	int ret, flen, proglen, pass, ulen = 0;
+	regmatch_t pmatch[1];
+	unsigned long base;
+	regex_t regex;
+	uint8_t *image;
+
+	if (hlen == 0)
+		return NULL;
+
+	ret = regcomp(&regex, "flen=[[:alnum:]]+ proglen=[[:digit:]]+ "
+		      "pass=[[:digit:]]+ image=[[:xdigit:]]+", REG_EXTENDED);
+	assert(ret == 0);
+
+	ptr = haystack;
+	memset(pmatch, 0, sizeof(pmatch));
+
+	while (1) {
+		ret = regexec(&regex, ptr, 1, pmatch, 0);
+		if (ret == 0) {
+			ptr += pmatch[0].rm_eo;
+			off += pmatch[0].rm_eo;
+			assert(off < hlen);
+		} else
+			break;
+	}
+
+	ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so);
+	ret = sscanf(ptr, "flen=%d proglen=%d pass=%d image=%lx",
+		     &flen, &proglen, &pass, &base);
+	if (ret != 4) {
+		regfree(&regex);
+		return NULL;
+	}
+	if (proglen > 1000000) {
+		printf("proglen of %d too big, stopping\n", proglen);
+		return NULL;
+	}
+
+	image = malloc(proglen);
+	if (!image) {
+		printf("Out of memory\n");
+		return NULL;
+	}
+	memset(image, 0, proglen);
+
+	tmp = ptr = haystack + off;
+	while ((ptr = strtok(tmp, "\n")) != NULL && ulen < proglen) {
+		tmp = NULL;
+		if (!strstr(ptr, "JIT code"))
+			continue;
+		pptr = ptr;
+		while ((ptr = strstr(pptr, ":")))
+			pptr = ptr + 1;
+		ptr = pptr;
+		do {
+			image[ulen++] = (uint8_t) strtoul(pptr, &pptr, 16);
+			if (ptr == pptr) {
+				ulen--;
+				break;
+			}
+			if (ulen >= proglen)
+				break;
+			ptr = pptr;
+		} while (1);
+	}
+
+	assert(ulen == proglen);
+	printf("%d bytes emitted from JIT compiler (pass:%d, flen:%d)\n",
+	       proglen, pass, flen);
+	printf("%lx + <x>:\n", base);
+
+	regfree(&regex);
+	*ilen = ulen;
+	return image;
+}
+
+static void usage(void)
+{
+	printf("Usage: bpf_jit_disasm [...]\n");
+	printf("       -o          Also display related opcodes (default: off).\n");
+	printf("       -O <file>   Write binary image of code to file, don't disassemble to stdout.\n");
+	printf("       -f <file>   Read last image dump from file or stdin (default: klog).\n");
+	printf("       -h          Display this help.\n");
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int len, klen, opt, opcodes = 0;
+	char *kbuff, *file = NULL;
+	char *ofile = NULL;
+	int ofd;
+	ssize_t nr;
+	uint8_t *pos;
+	uint8_t *image = NULL;
+
+	while ((opt = getopt(argc, argv, "of:O:")) != -1) {
+		switch (opt) {
+		case 'o':
+			opcodes = 1;
+			break;
+		case 'O':
+			ofile = optarg;
+			break;
+		case 'f':
+			file = optarg;
+			break;
+		default:
+			usage();
+			return -1;
+		}
+	}
+
+	bfd_init();
+
+	kbuff = get_log_buff(file, &klen);
+	if (!kbuff) {
+		fprintf(stderr, "Could not retrieve log buffer!\n");
+		return -1;
+	}
+
+	image = get_last_jit_image(kbuff, klen, &len);
+	if (!image) {
+		fprintf(stderr, "No JIT image found!\n");
+		goto done;
+	}
+	if (!ofile) {
+		get_asm_insns(image, len, opcodes);
+		goto done;
+	}
+
+	ofd = open(ofile, O_WRONLY | O_CREAT | O_TRUNC, DEFFILEMODE);
+	if (ofd < 0) {
+		fprintf(stderr, "Could not open file %s for writing: ", ofile);
+		perror(NULL);
+		goto done;
+	}
+	pos = image;
+	do {
+		nr = write(ofd, pos, len);
+		if (nr < 0) {
+			fprintf(stderr, "Could not write data to %s: ", ofile);
+			perror(NULL);
+			goto done;
+		}
+		len -= nr;
+		pos += nr;
+	} while (len);
+	close(ofd);
+
+done:
+	put_log_buff(kbuff);
+	free(image);
+	return 0;
+}
diff --git a/tools/net/Makefile b/tools/net/Makefile
deleted file mode 100644
index ddf888010652..000000000000
--- a/tools/net/Makefile
+++ /dev/null
@@ -1,35 +0,0 @@
-prefix = /usr
-
-CC = gcc
-LEX = flex
-YACC = bison
-
-CFLAGS += -Wall -O2
-CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
-
-%.yacc.c: %.y
-	$(YACC) -o $@ -d $<
-
-%.lex.c: %.l
-	$(LEX) -o $@ $<
-
-all : bpf_jit_disasm bpf_dbg bpf_asm
-
-bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
-bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
-bpf_jit_disasm : bpf_jit_disasm.o
-
-bpf_dbg : LDLIBS = -lreadline
-bpf_dbg : bpf_dbg.o
-
-bpf_asm : LDLIBS =
-bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
-bpf_exp.lex.o : bpf_exp.yacc.c
-
-clean :
-	rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
-
-install :
-	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
-	install bpf_dbg $(prefix)/bin/bpf_dbg
-	install bpf_asm $(prefix)/bin/bpf_asm
diff --git a/tools/net/bpf_asm.c b/tools/net/bpf_asm.c
deleted file mode 100644
index c15aef097b04..000000000000
--- a/tools/net/bpf_asm.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Minimal BPF assembler
- *
- * Instead of libpcap high-level filter expressions, it can be quite
- * useful to define filters in low-level BPF assembler (that is kept
- * close to Steven McCanne and Van Jacobson's original BPF paper).
- * In particular for BPF JIT implementors, JIT security auditors, or
- * just for defining BPF expressions that contain extensions which are
- * not supported by compilers.
- *
- * How to get into it:
- *
- * 1) read Documentation/networking/filter.txt
- * 2) Run `bpf_asm [-c] <filter-prog file>` to translate into binary
- *    blob that is loadable with xt_bpf, cls_bpf et al. Note: -c will
- *    pretty print a C-like construct.
- *
- * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-#include <stdbool.h>
-#include <stdio.h>
-#include <string.h>
-
-extern void bpf_asm_compile(FILE *fp, bool cstyle);
-
-int main(int argc, char **argv)
-{
-	FILE *fp = stdin;
-	bool cstyle = false;
-	int i;
-
-	for (i = 1; i < argc; i++) {
-		if (!strncmp("-c", argv[i], 2)) {
-			cstyle = true;
-			continue;
-		}
-
-		fp = fopen(argv[i], "r");
-		if (!fp) {
-			fp = stdin;
-			continue;
-		}
-
-		break;
-	}
-
-	bpf_asm_compile(fp, cstyle);
-
-	return 0;
-}
diff --git a/tools/net/bpf_dbg.c b/tools/net/bpf_dbg.c
deleted file mode 100644
index 4f254bcc4423..000000000000
--- a/tools/net/bpf_dbg.c
+++ /dev/null
@@ -1,1395 +0,0 @@
-/*
- * Minimal BPF debugger
- *
- * Minimal BPF debugger that mimics the kernel's engine (w/o extensions)
- * and allows for single stepping through selected packets from a pcap
- * with a provided user filter in order to facilitate verification of a
- * BPF program. Besides others, this is useful to verify BPF programs
- * before attaching to a live system, and can be used in socket filters,
- * cls_bpf, xt_bpf, team driver and e.g. PTP code; in particular when a
- * single more complex BPF program is being used. Reasons for a more
- * complex BPF program are likely primarily to optimize execution time
- * for making a verdict when multiple simple BPF programs are combined
- * into one in order to prevent parsing same headers multiple times.
- *
- * More on how to debug BPF opcodes see Documentation/networking/filter.txt
- * which is the main document on BPF. Mini howto for getting started:
- *
- *  1) `./bpf_dbg` to enter the shell (shell cmds denoted with '>'):
- *  2) > load bpf 6,40 0 0 12,21 0 3 20... (output from `bpf_asm` or
- *     `tcpdump -iem1 -ddd port 22 | tr '\n' ','` to load as filter)
- *  3) > load pcap foo.pcap
- *  4) > run <n>/disassemble/dump/quit (self-explanatory)
- *  5) > breakpoint 2 (sets bp at loaded BPF insns 2, do `run` then;
- *       multiple bps can be set, of course, a call to `breakpoint`
- *       w/o args shows currently loaded bps, `breakpoint reset` for
- *       resetting all breakpoints)
- *  6) > select 3 (`run` etc will start from the 3rd packet in the pcap)
- *  7) > step [-<n>, +<n>] (performs single stepping through the BPF)
- *
- * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-#include <stdio.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <ctype.h>
-#include <stdbool.h>
-#include <stdarg.h>
-#include <setjmp.h>
-#include <linux/filter.h>
-#include <linux/if_packet.h>
-#include <readline/readline.h>
-#include <readline/history.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <signal.h>
-#include <arpa/inet.h>
-#include <net/ethernet.h>
-
-#define TCPDUMP_MAGIC	0xa1b2c3d4
-
-#define BPF_LDX_B	(BPF_LDX | BPF_B)
-#define BPF_LDX_W	(BPF_LDX | BPF_W)
-#define BPF_JMP_JA	(BPF_JMP | BPF_JA)
-#define BPF_JMP_JEQ	(BPF_JMP | BPF_JEQ)
-#define BPF_JMP_JGT	(BPF_JMP | BPF_JGT)
-#define BPF_JMP_JGE	(BPF_JMP | BPF_JGE)
-#define BPF_JMP_JSET	(BPF_JMP | BPF_JSET)
-#define BPF_ALU_ADD	(BPF_ALU | BPF_ADD)
-#define BPF_ALU_SUB	(BPF_ALU | BPF_SUB)
-#define BPF_ALU_MUL	(BPF_ALU | BPF_MUL)
-#define BPF_ALU_DIV	(BPF_ALU | BPF_DIV)
-#define BPF_ALU_MOD	(BPF_ALU | BPF_MOD)
-#define BPF_ALU_NEG	(BPF_ALU | BPF_NEG)
-#define BPF_ALU_AND	(BPF_ALU | BPF_AND)
-#define BPF_ALU_OR	(BPF_ALU | BPF_OR)
-#define BPF_ALU_XOR	(BPF_ALU | BPF_XOR)
-#define BPF_ALU_LSH	(BPF_ALU | BPF_LSH)
-#define BPF_ALU_RSH	(BPF_ALU | BPF_RSH)
-#define BPF_MISC_TAX	(BPF_MISC | BPF_TAX)
-#define BPF_MISC_TXA	(BPF_MISC | BPF_TXA)
-#define BPF_LD_B	(BPF_LD | BPF_B)
-#define BPF_LD_H	(BPF_LD | BPF_H)
-#define BPF_LD_W	(BPF_LD | BPF_W)
-
-#ifndef array_size
-# define array_size(x)	(sizeof(x) / sizeof((x)[0]))
-#endif
-
-#ifndef __check_format_printf
-# define __check_format_printf(pos_fmtstr, pos_fmtargs) \
-	__attribute__ ((format (printf, (pos_fmtstr), (pos_fmtargs))))
-#endif
-
-enum {
-	CMD_OK,
-	CMD_ERR,
-	CMD_EX,
-};
-
-struct shell_cmd {
-	const char *name;
-	int (*func)(char *args);
-};
-
-struct pcap_filehdr {
-	uint32_t magic;
-	uint16_t version_major;
-	uint16_t version_minor;
-	int32_t  thiszone;
-	uint32_t sigfigs;
-	uint32_t snaplen;
-	uint32_t linktype;
-};
-
-struct pcap_timeval {
-	int32_t tv_sec;
-	int32_t tv_usec;
-};
-
-struct pcap_pkthdr {
-	struct pcap_timeval ts;
-	uint32_t caplen;
-	uint32_t len;
-};
-
-struct bpf_regs {
-	uint32_t A;
-	uint32_t X;
-	uint32_t M[BPF_MEMWORDS];
-	uint32_t R;
-	bool     Rs;
-	uint16_t Pc;
-};
-
-static struct sock_filter bpf_image[BPF_MAXINSNS + 1];
-static unsigned int bpf_prog_len;
-
-static int bpf_breakpoints[64];
-static struct bpf_regs bpf_regs[BPF_MAXINSNS + 1];
-static struct bpf_regs bpf_curr;
-static unsigned int bpf_regs_len;
-
-static int pcap_fd = -1;
-static unsigned int pcap_packet;
-static size_t pcap_map_size;
-static char *pcap_ptr_va_start, *pcap_ptr_va_curr;
-
-static const char * const op_table[] = {
-	[BPF_ST]	= "st",
-	[BPF_STX]	= "stx",
-	[BPF_LD_B]	= "ldb",
-	[BPF_LD_H]	= "ldh",
-	[BPF_LD_W]	= "ld",
-	[BPF_LDX]	= "ldx",
-	[BPF_LDX_B]	= "ldxb",
-	[BPF_JMP_JA]	= "ja",
-	[BPF_JMP_JEQ]	= "jeq",
-	[BPF_JMP_JGT]	= "jgt",
-	[BPF_JMP_JGE]	= "jge",
-	[BPF_JMP_JSET]	= "jset",
-	[BPF_ALU_ADD]	= "add",
-	[BPF_ALU_SUB]	= "sub",
-	[BPF_ALU_MUL]	= "mul",
-	[BPF_ALU_DIV]	= "div",
-	[BPF_ALU_MOD]	= "mod",
-	[BPF_ALU_NEG]	= "neg",
-	[BPF_ALU_AND]	= "and",
-	[BPF_ALU_OR]	= "or",
-	[BPF_ALU_XOR]	= "xor",
-	[BPF_ALU_LSH]	= "lsh",
-	[BPF_ALU_RSH]	= "rsh",
-	[BPF_MISC_TAX]	= "tax",
-	[BPF_MISC_TXA]	= "txa",
-	[BPF_RET]	= "ret",
-};
-
-static __check_format_printf(1, 2) int rl_printf(const char *fmt, ...)
-{
-	int ret;
-	va_list vl;
-
-	va_start(vl, fmt);
-	ret = vfprintf(rl_outstream, fmt, vl);
-	va_end(vl);
-
-	return ret;
-}
-
-static int matches(const char *cmd, const char *pattern)
-{
-	int len = strlen(cmd);
-
-	if (len > strlen(pattern))
-		return -1;
-
-	return memcmp(pattern, cmd, len);
-}
-
-static void hex_dump(const uint8_t *buf, size_t len)
-{
-	int i;
-
-	rl_printf("%3u: ", 0);
-	for (i = 0; i < len; i++) {
-		if (i && !(i % 16))
-			rl_printf("\n%3u: ", i);
-		rl_printf("%02x ", buf[i]);
-	}
-	rl_printf("\n");
-}
-
-static bool bpf_prog_loaded(void)
-{
-	if (bpf_prog_len == 0)
-		rl_printf("no bpf program loaded!\n");
-
-	return bpf_prog_len > 0;
-}
-
-static void bpf_disasm(const struct sock_filter f, unsigned int i)
-{
-	const char *op, *fmt;
-	int val = f.k;
-	char buf[256];
-
-	switch (f.code) {
-	case BPF_RET | BPF_K:
-		op = op_table[BPF_RET];
-		fmt = "#%#x";
-		break;
-	case BPF_RET | BPF_A:
-		op = op_table[BPF_RET];
-		fmt = "a";
-		break;
-	case BPF_RET | BPF_X:
-		op = op_table[BPF_RET];
-		fmt = "x";
-		break;
-	case BPF_MISC_TAX:
-		op = op_table[BPF_MISC_TAX];
-		fmt = "";
-		break;
-	case BPF_MISC_TXA:
-		op = op_table[BPF_MISC_TXA];
-		fmt = "";
-		break;
-	case BPF_ST:
-		op = op_table[BPF_ST];
-		fmt = "M[%d]";
-		break;
-	case BPF_STX:
-		op = op_table[BPF_STX];
-		fmt = "M[%d]";
-		break;
-	case BPF_LD_W | BPF_ABS:
-		op = op_table[BPF_LD_W];
-		fmt = "[%d]";
-		break;
-	case BPF_LD_H | BPF_ABS:
-		op = op_table[BPF_LD_H];
-		fmt = "[%d]";
-		break;
-	case BPF_LD_B | BPF_ABS:
-		op = op_table[BPF_LD_B];
-		fmt = "[%d]";
-		break;
-	case BPF_LD_W | BPF_LEN:
-		op = op_table[BPF_LD_W];
-		fmt = "#len";
-		break;
-	case BPF_LD_W | BPF_IND:
-		op = op_table[BPF_LD_W];
-		fmt = "[x+%d]";
-		break;
-	case BPF_LD_H | BPF_IND:
-		op = op_table[BPF_LD_H];
-		fmt = "[x+%d]";
-		break;
-	case BPF_LD_B | BPF_IND:
-		op = op_table[BPF_LD_B];
-		fmt = "[x+%d]";
-		break;
-	case BPF_LD | BPF_IMM:
-		op = op_table[BPF_LD_W];
-		fmt = "#%#x";
-		break;
-	case BPF_LDX | BPF_IMM:
-		op = op_table[BPF_LDX];
-		fmt = "#%#x";
-		break;
-	case BPF_LDX_B | BPF_MSH:
-		op = op_table[BPF_LDX_B];
-		fmt = "4*([%d]&0xf)";
-		break;
-	case BPF_LD | BPF_MEM:
-		op = op_table[BPF_LD_W];
-		fmt = "M[%d]";
-		break;
-	case BPF_LDX | BPF_MEM:
-		op = op_table[BPF_LDX];
-		fmt = "M[%d]";
-		break;
-	case BPF_JMP_JA:
-		op = op_table[BPF_JMP_JA];
-		fmt = "%d";
-		val = i + 1 + f.k;
-		break;
-	case BPF_JMP_JGT | BPF_X:
-		op = op_table[BPF_JMP_JGT];
-		fmt = "x";
-		break;
-	case BPF_JMP_JGT | BPF_K:
-		op = op_table[BPF_JMP_JGT];
-		fmt = "#%#x";
-		break;
-	case BPF_JMP_JGE | BPF_X:
-		op = op_table[BPF_JMP_JGE];
-		fmt = "x";
-		break;
-	case BPF_JMP_JGE | BPF_K:
-		op = op_table[BPF_JMP_JGE];
-		fmt = "#%#x";
-		break;
-	case BPF_JMP_JEQ | BPF_X:
-		op = op_table[BPF_JMP_JEQ];
-		fmt = "x";
-		break;
-	case BPF_JMP_JEQ | BPF_K:
-		op = op_table[BPF_JMP_JEQ];
-		fmt = "#%#x";
-		break;
-	case BPF_JMP_JSET | BPF_X:
-		op = op_table[BPF_JMP_JSET];
-		fmt = "x";
-		break;
-	case BPF_JMP_JSET | BPF_K:
-		op = op_table[BPF_JMP_JSET];
-		fmt = "#%#x";
-		break;
-	case BPF_ALU_NEG:
-		op = op_table[BPF_ALU_NEG];
-		fmt = "";
-		break;
-	case BPF_ALU_LSH | BPF_X:
-		op = op_table[BPF_ALU_LSH];
-		fmt = "x";
-		break;
-	case BPF_ALU_LSH | BPF_K:
-		op = op_table[BPF_ALU_LSH];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_RSH | BPF_X:
-		op = op_table[BPF_ALU_RSH];
-		fmt = "x";
-		break;
-	case BPF_ALU_RSH | BPF_K:
-		op = op_table[BPF_ALU_RSH];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_ADD | BPF_X:
-		op = op_table[BPF_ALU_ADD];
-		fmt = "x";
-		break;
-	case BPF_ALU_ADD | BPF_K:
-		op = op_table[BPF_ALU_ADD];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_SUB | BPF_X:
-		op = op_table[BPF_ALU_SUB];
-		fmt = "x";
-		break;
-	case BPF_ALU_SUB | BPF_K:
-		op = op_table[BPF_ALU_SUB];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_MUL | BPF_X:
-		op = op_table[BPF_ALU_MUL];
-		fmt = "x";
-		break;
-	case BPF_ALU_MUL | BPF_K:
-		op = op_table[BPF_ALU_MUL];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_DIV | BPF_X:
-		op = op_table[BPF_ALU_DIV];
-		fmt = "x";
-		break;
-	case BPF_ALU_DIV | BPF_K:
-		op = op_table[BPF_ALU_DIV];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_MOD | BPF_X:
-		op = op_table[BPF_ALU_MOD];
-		fmt = "x";
-		break;
-	case BPF_ALU_MOD | BPF_K:
-		op = op_table[BPF_ALU_MOD];
-		fmt = "#%d";
-		break;
-	case BPF_ALU_AND | BPF_X:
-		op = op_table[BPF_ALU_AND];
-		fmt = "x";
-		break;
-	case BPF_ALU_AND | BPF_K:
-		op = op_table[BPF_ALU_AND];
-		fmt = "#%#x";
-		break;
-	case BPF_ALU_OR | BPF_X:
-		op = op_table[BPF_ALU_OR];
-		fmt = "x";
-		break;
-	case BPF_ALU_OR | BPF_K:
-		op = op_table[BPF_ALU_OR];
-		fmt = "#%#x";
-		break;
-	case BPF_ALU_XOR | BPF_X:
-		op = op_table[BPF_ALU_XOR];
-		fmt = "x";
-		break;
-	case BPF_ALU_XOR | BPF_K:
-		op = op_table[BPF_ALU_XOR];
-		fmt = "#%#x";
-		break;
-	default:
-		op = "nosup";
-		fmt = "%#x";
-		val = f.code;
-		break;
-	}
-
-	memset(buf, 0, sizeof(buf));
-	snprintf(buf, sizeof(buf), fmt, val);
-	buf[sizeof(buf) - 1] = 0;
-
-	if ((BPF_CLASS(f.code) == BPF_JMP && BPF_OP(f.code) != BPF_JA))
-		rl_printf("l%d:\t%s %s, l%d, l%d\n", i, op, buf,
-			  i + 1 + f.jt, i + 1 + f.jf);
-	else
-		rl_printf("l%d:\t%s %s\n", i, op, buf);
-}
-
-static void bpf_dump_curr(struct bpf_regs *r, struct sock_filter *f)
-{
-	int i, m = 0;
-
-	rl_printf("pc:       [%u]\n", r->Pc);
-	rl_printf("code:     [%u] jt[%u] jf[%u] k[%u]\n",
-		  f->code, f->jt, f->jf, f->k);
-	rl_printf("curr:     ");
-	bpf_disasm(*f, r->Pc);
-
-	if (f->jt || f->jf) {
-		rl_printf("jt:       ");
-		bpf_disasm(*(f + f->jt + 1), r->Pc + f->jt + 1);
-		rl_printf("jf:       ");
-		bpf_disasm(*(f + f->jf + 1), r->Pc + f->jf + 1);
-	}
-
-	rl_printf("A:        [%#08x][%u]\n", r->A, r->A);
-	rl_printf("X:        [%#08x][%u]\n", r->X, r->X);
-	if (r->Rs)
-		rl_printf("ret:      [%#08x][%u]!\n", r->R, r->R);
-
-	for (i = 0; i < BPF_MEMWORDS; i++) {
-		if (r->M[i]) {
-			m++;
-			rl_printf("M[%d]: [%#08x][%u]\n", i, r->M[i], r->M[i]);
-		}
-	}
-	if (m == 0)
-		rl_printf("M[0,%d]:  [%#08x][%u]\n", BPF_MEMWORDS - 1, 0, 0);
-}
-
-static void bpf_dump_pkt(uint8_t *pkt, uint32_t pkt_caplen, uint32_t pkt_len)
-{
-	if (pkt_caplen != pkt_len)
-		rl_printf("cap: %u, len: %u\n", pkt_caplen, pkt_len);
-	else
-		rl_printf("len: %u\n", pkt_len);
-
-	hex_dump(pkt, pkt_caplen);
-}
-
-static void bpf_disasm_all(const struct sock_filter *f, unsigned int len)
-{
-	unsigned int i;
-
-	for (i = 0; i < len; i++)
-		bpf_disasm(f[i], i);
-}
-
-static void bpf_dump_all(const struct sock_filter *f, unsigned int len)
-{
-	unsigned int i;
-
-	rl_printf("/* { op, jt, jf, k }, */\n");
-	for (i = 0; i < len; i++)
-		rl_printf("{ %#04x, %2u, %2u, %#010x },\n",
-			  f[i].code, f[i].jt, f[i].jf, f[i].k);
-}
-
-static bool bpf_runnable(struct sock_filter *f, unsigned int len)
-{
-	int sock, ret, i;
-	struct sock_fprog bpf = {
-		.filter = f,
-		.len = len,
-	};
-
-	sock = socket(AF_INET, SOCK_DGRAM, 0);
-	if (sock < 0) {
-		rl_printf("cannot open socket!\n");
-		return false;
-	}
-	ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf));
-	close(sock);
-	if (ret < 0) {
-		rl_printf("program not allowed to run by kernel!\n");
-		return false;
-	}
-	for (i = 0; i < len; i++) {
-		if (BPF_CLASS(f[i].code) == BPF_LD &&
-		    f[i].k > SKF_AD_OFF) {
-			rl_printf("extensions currently not supported!\n");
-			return false;
-		}
-	}
-
-	return true;
-}
-
-static void bpf_reset_breakpoints(void)
-{
-	int i;
-
-	for (i = 0; i < array_size(bpf_breakpoints); i++)
-		bpf_breakpoints[i] = -1;
-}
-
-static void bpf_set_breakpoints(unsigned int where)
-{
-	int i;
-	bool set = false;
-
-	for (i = 0; i < array_size(bpf_breakpoints); i++) {
-		if (bpf_breakpoints[i] == (int) where) {
-			rl_printf("breakpoint already set!\n");
-			set = true;
-			break;
-		}
-
-		if (bpf_breakpoints[i] == -1 && set == false) {
-			bpf_breakpoints[i] = where;
-			set = true;
-		}
-	}
-
-	if (!set)
-		rl_printf("too many breakpoints set, reset first!\n");
-}
-
-static void bpf_dump_breakpoints(void)
-{
-	int i;
-
-	rl_printf("breakpoints: ");
-
-	for (i = 0; i < array_size(bpf_breakpoints); i++) {
-		if (bpf_breakpoints[i] < 0)
-			continue;
-		rl_printf("%d ", bpf_breakpoints[i]);
-	}
-
-	rl_printf("\n");
-}
-
-static void bpf_reset(void)
-{
-	bpf_regs_len = 0;
-
-	memset(bpf_regs, 0, sizeof(bpf_regs));
-	memset(&bpf_curr, 0, sizeof(bpf_curr));
-}
-
-static void bpf_safe_regs(void)
-{
-	memcpy(&bpf_regs[bpf_regs_len++], &bpf_curr, sizeof(bpf_curr));
-}
-
-static bool bpf_restore_regs(int off)
-{
-	unsigned int index = bpf_regs_len - 1 + off;
-
-	if (index == 0) {
-		bpf_reset();
-		return true;
-	} else if (index < bpf_regs_len) {
-		memcpy(&bpf_curr, &bpf_regs[index], sizeof(bpf_curr));
-		bpf_regs_len = index;
-		return true;
-	} else {
-		rl_printf("reached bottom of register history stack!\n");
-		return false;
-	}
-}
-
-static uint32_t extract_u32(uint8_t *pkt, uint32_t off)
-{
-	uint32_t r;
-
-	memcpy(&r, &pkt[off], sizeof(r));
-
-	return ntohl(r);
-}
-
-static uint16_t extract_u16(uint8_t *pkt, uint32_t off)
-{
-	uint16_t r;
-
-	memcpy(&r, &pkt[off], sizeof(r));
-
-	return ntohs(r);
-}
-
-static uint8_t extract_u8(uint8_t *pkt, uint32_t off)
-{
-	return pkt[off];
-}
-
-static void set_return(struct bpf_regs *r)
-{
-	r->R = 0;
-	r->Rs = true;
-}
-
-static void bpf_single_step(struct bpf_regs *r, struct sock_filter *f,
-			    uint8_t *pkt, uint32_t pkt_caplen,
-			    uint32_t pkt_len)
-{
-	uint32_t K = f->k;
-	int d;
-
-	switch (f->code) {
-	case BPF_RET | BPF_K:
-		r->R = K;
-		r->Rs = true;
-		break;
-	case BPF_RET | BPF_A:
-		r->R = r->A;
-		r->Rs = true;
-		break;
-	case BPF_RET | BPF_X:
-		r->R = r->X;
-		r->Rs = true;
-		break;
-	case BPF_MISC_TAX:
-		r->X = r->A;
-		break;
-	case BPF_MISC_TXA:
-		r->A = r->X;
-		break;
-	case BPF_ST:
-		r->M[K] = r->A;
-		break;
-	case BPF_STX:
-		r->M[K] = r->X;
-		break;
-	case BPF_LD_W | BPF_ABS:
-		d = pkt_caplen - K;
-		if (d >= sizeof(uint32_t))
-			r->A = extract_u32(pkt, K);
-		else
-			set_return(r);
-		break;
-	case BPF_LD_H | BPF_ABS:
-		d = pkt_caplen - K;
-		if (d >= sizeof(uint16_t))
-			r->A = extract_u16(pkt, K);
-		else
-			set_return(r);
-		break;
-	case BPF_LD_B | BPF_ABS:
-		d = pkt_caplen - K;
-		if (d >= sizeof(uint8_t))
-			r->A = extract_u8(pkt, K);
-		else
-			set_return(r);
-		break;
-	case BPF_LD_W | BPF_IND:
-		d = pkt_caplen - (r->X + K);
-		if (d >= sizeof(uint32_t))
-			r->A = extract_u32(pkt, r->X + K);
-		break;
-	case BPF_LD_H | BPF_IND:
-		d = pkt_caplen - (r->X + K);
-		if (d >= sizeof(uint16_t))
-			r->A = extract_u16(pkt, r->X + K);
-		else
-			set_return(r);
-		break;
-	case BPF_LD_B | BPF_IND:
-		d = pkt_caplen - (r->X + K);
-		if (d >= sizeof(uint8_t))
-			r->A = extract_u8(pkt, r->X + K);
-		else
-			set_return(r);
-		break;
-	case BPF_LDX_B | BPF_MSH:
-		d = pkt_caplen - K;
-		if (d >= sizeof(uint8_t)) {
-			r->X = extract_u8(pkt, K);
-			r->X = (r->X & 0xf) << 2;
-		} else
-			set_return(r);
-		break;
-	case BPF_LD_W | BPF_LEN:
-		r->A = pkt_len;
-		break;
-	case BPF_LDX_W | BPF_LEN:
-		r->A = pkt_len;
-		break;
-	case BPF_LD | BPF_IMM:
-		r->A = K;
-		break;
-	case BPF_LDX | BPF_IMM:
-		r->X = K;
-		break;
-	case BPF_LD | BPF_MEM:
-		r->A = r->M[K];
-		break;
-	case BPF_LDX | BPF_MEM:
-		r->X = r->M[K];
-		break;
-	case BPF_JMP_JA:
-		r->Pc += K;
-		break;
-	case BPF_JMP_JGT | BPF_X:
-		r->Pc += r->A > r->X ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JGT | BPF_K:
-		r->Pc += r->A > K ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JGE | BPF_X:
-		r->Pc += r->A >= r->X ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JGE | BPF_K:
-		r->Pc += r->A >= K ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JEQ | BPF_X:
-		r->Pc += r->A == r->X ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JEQ | BPF_K:
-		r->Pc += r->A == K ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JSET | BPF_X:
-		r->Pc += r->A & r->X ? f->jt : f->jf;
-		break;
-	case BPF_JMP_JSET | BPF_K:
-		r->Pc += r->A & K ? f->jt : f->jf;
-		break;
-	case BPF_ALU_NEG:
-		r->A = -r->A;
-		break;
-	case BPF_ALU_LSH | BPF_X:
-		r->A <<= r->X;
-		break;
-	case BPF_ALU_LSH | BPF_K:
-		r->A <<= K;
-		break;
-	case BPF_ALU_RSH | BPF_X:
-		r->A >>= r->X;
-		break;
-	case BPF_ALU_RSH | BPF_K:
-		r->A >>= K;
-		break;
-	case BPF_ALU_ADD | BPF_X:
-		r->A += r->X;
-		break;
-	case BPF_ALU_ADD | BPF_K:
-		r->A += K;
-		break;
-	case BPF_ALU_SUB | BPF_X:
-		r->A -= r->X;
-		break;
-	case BPF_ALU_SUB | BPF_K:
-		r->A -= K;
-		break;
-	case BPF_ALU_MUL | BPF_X:
-		r->A *= r->X;
-		break;
-	case BPF_ALU_MUL | BPF_K:
-		r->A *= K;
-		break;
-	case BPF_ALU_DIV | BPF_X:
-	case BPF_ALU_MOD | BPF_X:
-		if (r->X == 0) {
-			set_return(r);
-			break;
-		}
-		goto do_div;
-	case BPF_ALU_DIV | BPF_K:
-	case BPF_ALU_MOD | BPF_K:
-		if (K == 0) {
-			set_return(r);
-			break;
-		}
-do_div:
-		switch (f->code) {
-		case BPF_ALU_DIV | BPF_X:
-			r->A /= r->X;
-			break;
-		case BPF_ALU_DIV | BPF_K:
-			r->A /= K;
-			break;
-		case BPF_ALU_MOD | BPF_X:
-			r->A %= r->X;
-			break;
-		case BPF_ALU_MOD | BPF_K:
-			r->A %= K;
-			break;
-		}
-		break;
-	case BPF_ALU_AND | BPF_X:
-		r->A &= r->X;
-		break;
-	case BPF_ALU_AND | BPF_K:
-		r->A &= K;
-		break;
-	case BPF_ALU_OR | BPF_X:
-		r->A |= r->X;
-		break;
-	case BPF_ALU_OR | BPF_K:
-		r->A |= K;
-		break;
-	case BPF_ALU_XOR | BPF_X:
-		r->A ^= r->X;
-		break;
-	case BPF_ALU_XOR | BPF_K:
-		r->A ^= K;
-		break;
-	}
-}
-
-static bool bpf_pc_has_breakpoint(uint16_t pc)
-{
-	int i;
-
-	for (i = 0; i < array_size(bpf_breakpoints); i++) {
-		if (bpf_breakpoints[i] < 0)
-			continue;
-		if (bpf_breakpoints[i] == pc)
-			return true;
-	}
-
-	return false;
-}
-
-static bool bpf_handle_breakpoint(struct bpf_regs *r, struct sock_filter *f,
-				  uint8_t *pkt, uint32_t pkt_caplen,
-				  uint32_t pkt_len)
-{
-	rl_printf("-- register dump --\n");
-	bpf_dump_curr(r, &f[r->Pc]);
-	rl_printf("-- packet dump --\n");
-	bpf_dump_pkt(pkt, pkt_caplen, pkt_len);
-	rl_printf("(breakpoint)\n");
-	return true;
-}
-
-static int bpf_run_all(struct sock_filter *f, uint16_t bpf_len, uint8_t *pkt,
-		       uint32_t pkt_caplen, uint32_t pkt_len)
-{
-	bool stop = false;
-
-	while (bpf_curr.Rs == false && stop == false) {
-		bpf_safe_regs();
-
-		if (bpf_pc_has_breakpoint(bpf_curr.Pc))
-			stop = bpf_handle_breakpoint(&bpf_curr, f, pkt,
-						     pkt_caplen, pkt_len);
-
-		bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen,
-				pkt_len);
-		bpf_curr.Pc++;
-	}
-
-	return stop ? -1 : bpf_curr.R;
-}
-
-static int bpf_run_stepping(struct sock_filter *f, uint16_t bpf_len,
-			    uint8_t *pkt, uint32_t pkt_caplen,
-			    uint32_t pkt_len, int next)
-{
-	bool stop = false;
-	int i = 1;
-
-	while (bpf_curr.Rs == false && stop == false) {
-		bpf_safe_regs();
-
-		if (i++ == next)
-			stop = bpf_handle_breakpoint(&bpf_curr, f, pkt,
-						     pkt_caplen, pkt_len);
-
-		bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen,
-				pkt_len);
-		bpf_curr.Pc++;
-	}
-
-	return stop ? -1 : bpf_curr.R;
-}
-
-static bool pcap_loaded(void)
-{
-	if (pcap_fd < 0)
-		rl_printf("no pcap file loaded!\n");
-
-	return pcap_fd >= 0;
-}
-
-static struct pcap_pkthdr *pcap_curr_pkt(void)
-{
-	return (void *) pcap_ptr_va_curr;
-}
-
-static bool pcap_next_pkt(void)
-{
-	struct pcap_pkthdr *hdr = pcap_curr_pkt();
-
-	if (pcap_ptr_va_curr + sizeof(*hdr) -
-	    pcap_ptr_va_start >= pcap_map_size)
-		return false;
-	if (hdr->caplen == 0 || hdr->len == 0 || hdr->caplen > hdr->len)
-		return false;
-	if (pcap_ptr_va_curr + sizeof(*hdr) + hdr->caplen -
-	    pcap_ptr_va_start >= pcap_map_size)
-		return false;
-
-	pcap_ptr_va_curr += (sizeof(*hdr) + hdr->caplen);
-	return true;
-}
-
-static void pcap_reset_pkt(void)
-{
-	pcap_ptr_va_curr = pcap_ptr_va_start + sizeof(struct pcap_filehdr);
-}
-
-static int try_load_pcap(const char *file)
-{
-	struct pcap_filehdr *hdr;
-	struct stat sb;
-	int ret;
-
-	pcap_fd = open(file, O_RDONLY);
-	if (pcap_fd < 0) {
-		rl_printf("cannot open pcap [%s]!\n", strerror(errno));
-		return CMD_ERR;
-	}
-
-	ret = fstat(pcap_fd, &sb);
-	if (ret < 0) {
-		rl_printf("cannot fstat pcap file!\n");
-		return CMD_ERR;
-	}
-
-	if (!S_ISREG(sb.st_mode)) {
-		rl_printf("not a regular pcap file, duh!\n");
-		return CMD_ERR;
-	}
-
-	pcap_map_size = sb.st_size;
-	if (pcap_map_size <= sizeof(struct pcap_filehdr)) {
-		rl_printf("pcap file too small!\n");
-		return CMD_ERR;
-	}
-
-	pcap_ptr_va_start = mmap(NULL, pcap_map_size, PROT_READ,
-				 MAP_SHARED | MAP_LOCKED, pcap_fd, 0);
-	if (pcap_ptr_va_start == MAP_FAILED) {
-		rl_printf("mmap of file failed!");
-		return CMD_ERR;
-	}
-
-	hdr = (void *) pcap_ptr_va_start;
-	if (hdr->magic != TCPDUMP_MAGIC) {
-		rl_printf("wrong pcap magic!\n");
-		return CMD_ERR;
-	}
-
-	pcap_reset_pkt();
-
-	return CMD_OK;
-
-}
-
-static void try_close_pcap(void)
-{
-	if (pcap_fd >= 0) {
-		munmap(pcap_ptr_va_start, pcap_map_size);
-		close(pcap_fd);
-
-		pcap_ptr_va_start = pcap_ptr_va_curr = NULL;
-		pcap_map_size = 0;
-		pcap_packet = 0;
-		pcap_fd = -1;
-	}
-}
-
-static int cmd_load_bpf(char *bpf_string)
-{
-	char sp, *token, separator = ',';
-	unsigned short bpf_len, i = 0;
-	struct sock_filter tmp;
-
-	bpf_prog_len = 0;
-	memset(bpf_image, 0, sizeof(bpf_image));
-
-	if (sscanf(bpf_string, "%hu%c", &bpf_len, &sp) != 2 ||
-	    sp != separator || bpf_len > BPF_MAXINSNS || bpf_len == 0) {
-		rl_printf("syntax error in head length encoding!\n");
-		return CMD_ERR;
-	}
-
-	token = bpf_string;
-	while ((token = strchr(token, separator)) && (++token)[0]) {
-		if (i >= bpf_len) {
-			rl_printf("program exceeds encoded length!\n");
-			return CMD_ERR;
-		}
-
-		if (sscanf(token, "%hu %hhu %hhu %u,",
-			   &tmp.code, &tmp.jt, &tmp.jf, &tmp.k) != 4) {
-			rl_printf("syntax error at instruction %d!\n", i);
-			return CMD_ERR;
-		}
-
-		bpf_image[i].code = tmp.code;
-		bpf_image[i].jt = tmp.jt;
-		bpf_image[i].jf = tmp.jf;
-		bpf_image[i].k = tmp.k;
-
-		i++;
-	}
-
-	if (i != bpf_len) {
-		rl_printf("syntax error exceeding encoded length!\n");
-		return CMD_ERR;
-	} else
-		bpf_prog_len = bpf_len;
-	if (!bpf_runnable(bpf_image, bpf_prog_len))
-		bpf_prog_len = 0;
-
-	return CMD_OK;
-}
-
-static int cmd_load_pcap(char *file)
-{
-	char *file_trim, *tmp;
-
-	file_trim = strtok_r(file, " ", &tmp);
-	if (file_trim == NULL)
-		return CMD_ERR;
-
-	try_close_pcap();
-
-	return try_load_pcap(file_trim);
-}
-
-static int cmd_load(char *arg)
-{
-	char *subcmd, *cont, *tmp = strdup(arg);
-	int ret = CMD_OK;
-
-	subcmd = strtok_r(tmp, " ", &cont);
-	if (subcmd == NULL)
-		goto out;
-	if (matches(subcmd, "bpf") == 0) {
-		bpf_reset();
-		bpf_reset_breakpoints();
-
-		ret = cmd_load_bpf(cont);
-	} else if (matches(subcmd, "pcap") == 0) {
-		ret = cmd_load_pcap(cont);
-	} else {
-out:
-		rl_printf("bpf <code>:  load bpf code\n");
-		rl_printf("pcap <file>: load pcap file\n");
-		ret = CMD_ERR;
-	}
-
-	free(tmp);
-	return ret;
-}
-
-static int cmd_step(char *num)
-{
-	struct pcap_pkthdr *hdr;
-	int steps, ret;
-
-	if (!bpf_prog_loaded() || !pcap_loaded())
-		return CMD_ERR;
-
-	steps = strtol(num, NULL, 10);
-	if (steps == 0 || strlen(num) == 0)
-		steps = 1;
-	if (steps < 0) {
-		if (!bpf_restore_regs(steps))
-			return CMD_ERR;
-		steps = 1;
-	}
-
-	hdr = pcap_curr_pkt();
-	ret = bpf_run_stepping(bpf_image, bpf_prog_len,
-			       (uint8_t *) hdr + sizeof(*hdr),
-			       hdr->caplen, hdr->len, steps);
-	if (ret >= 0 || bpf_curr.Rs) {
-		bpf_reset();
-		if (!pcap_next_pkt()) {
-			rl_printf("(going back to first packet)\n");
-			pcap_reset_pkt();
-		} else {
-			rl_printf("(next packet)\n");
-		}
-	}
-
-	return CMD_OK;
-}
-
-static int cmd_select(char *num)
-{
-	unsigned int which, i;
-	bool have_next = true;
-
-	if (!pcap_loaded() || strlen(num) == 0)
-		return CMD_ERR;
-
-	which = strtoul(num, NULL, 10);
-	if (which == 0) {
-		rl_printf("packet count starts with 1, clamping!\n");
-		which = 1;
-	}
-
-	pcap_reset_pkt();
-	bpf_reset();
-
-	for (i = 0; i < which && (have_next = pcap_next_pkt()); i++)
-		/* noop */;
-	if (!have_next || pcap_curr_pkt() == NULL) {
-		rl_printf("no packet #%u available!\n", which);
-		pcap_reset_pkt();
-		return CMD_ERR;
-	}
-
-	return CMD_OK;
-}
-
-static int cmd_breakpoint(char *subcmd)
-{
-	if (!bpf_prog_loaded())
-		return CMD_ERR;
-	if (strlen(subcmd) == 0)
-		bpf_dump_breakpoints();
-	else if (matches(subcmd, "reset") == 0)
-		bpf_reset_breakpoints();
-	else {
-		unsigned int where = strtoul(subcmd, NULL, 10);
-
-		if (where < bpf_prog_len) {
-			bpf_set_breakpoints(where);
-			rl_printf("breakpoint at: ");
-			bpf_disasm(bpf_image[where], where);
-		}
-	}
-
-	return CMD_OK;
-}
-
-static int cmd_run(char *num)
-{
-	static uint32_t pass, fail;
-	bool has_limit = true;
-	int pkts = 0, i = 0;
-
-	if (!bpf_prog_loaded() || !pcap_loaded())
-		return CMD_ERR;
-
-	pkts = strtol(num, NULL, 10);
-	if (pkts == 0 || strlen(num) == 0)
-		has_limit = false;
-
-	do {
-		struct pcap_pkthdr *hdr = pcap_curr_pkt();
-		int ret = bpf_run_all(bpf_image, bpf_prog_len,
-				      (uint8_t *) hdr + sizeof(*hdr),
-				      hdr->caplen, hdr->len);
-		if (ret > 0)
-			pass++;
-		else if (ret == 0)
-			fail++;
-		else
-			return CMD_OK;
-		bpf_reset();
-	} while (pcap_next_pkt() && (!has_limit || (has_limit && ++i < pkts)));
-
-	rl_printf("bpf passes:%u fails:%u\n", pass, fail);
-
-	pcap_reset_pkt();
-	bpf_reset();
-
-	pass = fail = 0;
-	return CMD_OK;
-}
-
-static int cmd_disassemble(char *line_string)
-{
-	bool single_line = false;
-	unsigned long line;
-
-	if (!bpf_prog_loaded())
-		return CMD_ERR;
-	if (strlen(line_string) > 0 &&
-	    (line = strtoul(line_string, NULL, 10)) < bpf_prog_len)
-		single_line = true;
-	if (single_line)
-		bpf_disasm(bpf_image[line], line);
-	else
-		bpf_disasm_all(bpf_image, bpf_prog_len);
-
-	return CMD_OK;
-}
-
-static int cmd_dump(char *dontcare)
-{
-	if (!bpf_prog_loaded())
-		return CMD_ERR;
-
-	bpf_dump_all(bpf_image, bpf_prog_len);
-
-	return CMD_OK;
-}
-
-static int cmd_quit(char *dontcare)
-{
-	return CMD_EX;
-}
-
-static const struct shell_cmd cmds[] = {
-	{ .name = "load", .func = cmd_load },
-	{ .name = "select", .func = cmd_select },
-	{ .name = "step", .func = cmd_step },
-	{ .name = "run", .func = cmd_run },
-	{ .name = "breakpoint", .func = cmd_breakpoint },
-	{ .name = "disassemble", .func = cmd_disassemble },
-	{ .name = "dump", .func = cmd_dump },
-	{ .name = "quit", .func = cmd_quit },
-};
-
-static int execf(char *arg)
-{
-	char *cmd, *cont, *tmp = strdup(arg);
-	int i, ret = 0, len;
-
-	cmd = strtok_r(tmp, " ", &cont);
-	if (cmd == NULL)
-		goto out;
-	len = strlen(cmd);
-	for (i = 0; i < array_size(cmds); i++) {
-		if (len != strlen(cmds[i].name))
-			continue;
-		if (strncmp(cmds[i].name, cmd, len) == 0) {
-			ret = cmds[i].func(cont);
-			break;
-		}
-	}
-out:
-	free(tmp);
-	return ret;
-}
-
-static char *shell_comp_gen(const char *buf, int state)
-{
-	static int list_index, len;
-
-	if (!state) {
-		list_index = 0;
-		len = strlen(buf);
-	}
-
-	for (; list_index < array_size(cmds); ) {
-		const char *name = cmds[list_index].name;
-
-		list_index++;
-		if (strncmp(name, buf, len) == 0)
-			return strdup(name);
-	}
-
-	return NULL;
-}
-
-static char **shell_completion(const char *buf, int start, int end)
-{
-	char **matches = NULL;
-
-	if (start == 0)
-		matches = rl_completion_matches(buf, shell_comp_gen);
-
-	return matches;
-}
-
-static void intr_shell(int sig)
-{
-	if (rl_end)
-		rl_kill_line(-1, 0);
-
-	rl_crlf();
-	rl_refresh_line(0, 0);
-	rl_free_line_state();
-}
-
-static void init_shell(FILE *fin, FILE *fout)
-{
-	char file[128];
-
-	snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME"));
-	read_history(file);
-
-	rl_instream = fin;
-	rl_outstream = fout;
-
-	rl_readline_name = "bpf_dbg";
-	rl_terminal_name = getenv("TERM");
-
-	rl_catch_signals = 0;
-	rl_catch_sigwinch = 1;
-
-	rl_attempted_completion_function = shell_completion;
-
-	rl_bind_key('\t', rl_complete);
-
-	rl_bind_key_in_map('\t', rl_complete, emacs_meta_keymap);
-	rl_bind_key_in_map('\033', rl_complete, emacs_meta_keymap);
-
-	snprintf(file, sizeof(file), "%s/.bpf_dbg_init", getenv("HOME"));
-	rl_read_init_file(file);
-
-	rl_prep_terminal(0);
-	rl_set_signals();
-
-	signal(SIGINT, intr_shell);
-}
-
-static void exit_shell(FILE *fin, FILE *fout)
-{
-	char file[128];
-
-	snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME"));
-	write_history(file);
-
-	clear_history();
-	rl_deprep_terminal();
-
-	try_close_pcap();
-
-	if (fin != stdin)
-		fclose(fin);
-	if (fout != stdout)
-		fclose(fout);
-}
-
-static int run_shell_loop(FILE *fin, FILE *fout)
-{
-	char *buf;
-
-	init_shell(fin, fout);
-
-	while ((buf = readline("> ")) != NULL) {
-		int ret = execf(buf);
-		if (ret == CMD_EX)
-			break;
-		if (ret == CMD_OK && strlen(buf) > 0)
-			add_history(buf);
-
-		free(buf);
-	}
-
-	exit_shell(fin, fout);
-	return 0;
-}
-
-int main(int argc, char **argv)
-{
-	FILE *fin = NULL, *fout = NULL;
-
-	if (argc >= 2)
-		fin = fopen(argv[1], "r");
-	if (argc >= 3)
-		fout = fopen(argv[2], "w");
-
-	return run_shell_loop(fin ? : stdin, fout ? : stdout);
-}
diff --git a/tools/net/bpf_exp.l b/tools/net/bpf_exp.l
deleted file mode 100644
index bd83149e7be0..000000000000
--- a/tools/net/bpf_exp.l
+++ /dev/null
@@ -1,198 +0,0 @@
-/*
- * BPF asm code lexer
- *
- * This program is free software; you can distribute it and/or modify
- * it under the terms of the GNU General Public License as published
- * by the Free Software Foundation; either version 2 of the License,
- * or (at your option) any later version.
- *
- * Syntax kept close to:
- *
- * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
- * architecture for user-level packet capture. In Proceedings of the
- * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
- * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
- * CA, USA, 2-2.
- *
- * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-%{
-
-#include <stdio.h>
-#include <stdint.h>
-#include <stdlib.h>
-#include <string.h>
-
-#include <linux/filter.h>
-
-#include "bpf_exp.yacc.h"
-
-extern void yyerror(const char *str);
-
-%}
-
-%option align
-%option ecs
-
-%option nounput
-%option noreject
-%option noinput
-%option noyywrap
-
-%option 8bit
-%option caseless
-%option yylineno
-
-%%
-
-"ldb"		{ return OP_LDB; }
-"ldh"		{ return OP_LDH; }
-"ld"		{ return OP_LD; }
-"ldi"		{ return OP_LDI; }
-"ldx"		{ return OP_LDX; }
-"ldxi"		{ return OP_LDXI; }
-"ldxb"		{ return OP_LDXB; }
-"st"		{ return OP_ST; }
-"stx"		{ return OP_STX; }
-"jmp"		{ return OP_JMP; }
-"ja"		{ return OP_JMP; }
-"jeq"		{ return OP_JEQ; }
-"jneq"		{ return OP_JNEQ; }
-"jne"		{ return OP_JNEQ; }
-"jlt"		{ return OP_JLT; }
-"jle"		{ return OP_JLE; }
-"jgt"		{ return OP_JGT; }
-"jge"		{ return OP_JGE; }
-"jset"		{ return OP_JSET; }
-"add"		{ return OP_ADD; }
-"sub"		{ return OP_SUB; }
-"mul"		{ return OP_MUL; }
-"div"		{ return OP_DIV; }
-"mod"		{ return OP_MOD; }
-"neg"		{ return OP_NEG; }
-"and"		{ return OP_AND; }
-"xor"		{ return OP_XOR; }
-"or"		{ return OP_OR; }
-"lsh"		{ return OP_LSH; }
-"rsh"		{ return OP_RSH; }
-"ret"		{ return OP_RET; }
-"tax"		{ return OP_TAX; }
-"txa"		{ return OP_TXA; }
-
-"#"?("len")	{ return K_PKT_LEN; }
-
-"#"?("proto")	{
-		yylval.number = SKF_AD_PROTOCOL;
-		return extension;
-	}
-"#"?("type")	{
-		yylval.number = SKF_AD_PKTTYPE;
-		return extension;
-	}
-"#"?("poff")	{
-		yylval.number = SKF_AD_PAY_OFFSET;
-		return extension;
-	}
-"#"?("ifidx")	{
-		yylval.number = SKF_AD_IFINDEX;
-		return extension;
-	}
-"#"?("nla")	{
-		yylval.number = SKF_AD_NLATTR;
-		return extension;
-	}
-"#"?("nlan")	{
-		yylval.number = SKF_AD_NLATTR_NEST;
-		return extension;
-	}
-"#"?("mark")	{
-		yylval.number = SKF_AD_MARK;
-		return extension;
-	}
-"#"?("queue")	{
-		yylval.number = SKF_AD_QUEUE;
-		return extension;
-	}
-"#"?("hatype")	{
-		yylval.number = SKF_AD_HATYPE;
-		return extension;
-	}
-"#"?("rxhash")	{
-		yylval.number = SKF_AD_RXHASH;
-		return extension;
-	}
-"#"?("cpu")	{
-		yylval.number = SKF_AD_CPU;
-		return extension;
-	}
-"#"?("vlan_tci") {
-		yylval.number = SKF_AD_VLAN_TAG;
-		return extension;
-	}
-"#"?("vlan_pr")	{
-		yylval.number = SKF_AD_VLAN_TAG_PRESENT;
-		return extension;
-	}
-"#"?("vlan_avail") {
-		yylval.number = SKF_AD_VLAN_TAG_PRESENT;
-		return extension;
-	}
-"#"?("vlan_tpid") {
-		yylval.number = SKF_AD_VLAN_TPID;
-		return extension;
-	}
-"#"?("rand")	{
-		yylval.number = SKF_AD_RANDOM;
-		return extension;
-	}
-
-":"		{ return ':'; }
-","		{ return ','; }
-"#"		{ return '#'; }
-"%"		{ return '%'; }
-"["		{ return '['; }
-"]"		{ return ']'; }
-"("		{ return '('; }
-")"		{ return ')'; }
-"x"		{ return 'x'; }
-"a"		{ return 'a'; }
-"+"		{ return '+'; }
-"M"		{ return 'M'; }
-"*"		{ return '*'; }
-"&"		{ return '&'; }
-
-([0][x][a-fA-F0-9]+) {
-			yylval.number = strtoul(yytext, NULL, 16);
-			return number;
-		}
-([0][b][0-1]+)	{
-			yylval.number = strtol(yytext + 2, NULL, 2);
-			return number;
-		}
-(([0])|([-+]?[1-9][0-9]*)) {
-			yylval.number = strtol(yytext, NULL, 10);
-			return number;
-		}
-([0][0-9]+)	{
-			yylval.number = strtol(yytext + 1, NULL, 8);
-			return number;
-		}
-[a-zA-Z_][a-zA-Z0-9_]+ {
-			yylval.label = strdup(yytext);
-			return label;
-		}
-
-"/*"([^\*]|\*[^/])*"*/"		{ /* NOP */ }
-";"[^\n]*			{ /* NOP */ }
-^#.*				{ /* NOP */ }
-[ \t]+				{ /* NOP */ }
-[ \n]+				{ /* NOP */ }
-
-.		{
-			printf("unknown character \'%s\'", yytext);
-			yyerror("lex unknown character");
-		}
-
-%%
diff --git a/tools/net/bpf_exp.y b/tools/net/bpf_exp.y
deleted file mode 100644
index 56ba1de50784..000000000000
--- a/tools/net/bpf_exp.y
+++ /dev/null
@@ -1,656 +0,0 @@
-/*
- * BPF asm code parser
- *
- * This program is free software; you can distribute it and/or modify
- * it under the terms of the GNU General Public License as published
- * by the Free Software Foundation; either version 2 of the License,
- * or (at your option) any later version.
- *
- * Syntax kept close to:
- *
- * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
- * architecture for user-level packet capture. In Proceedings of the
- * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
- * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
- * CA, USA, 2-2.
- *
- * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-%{
-
-#include <stdio.h>
-#include <string.h>
-#include <stdint.h>
-#include <stdlib.h>
-#include <stdbool.h>
-#include <unistd.h>
-#include <errno.h>
-#include <assert.h>
-#include <linux/filter.h>
-
-#include "bpf_exp.yacc.h"
-
-enum jmp_type { JTL, JFL, JKL };
-
-extern FILE *yyin;
-extern int yylineno;
-extern int yylex(void);
-extern void yyerror(const char *str);
-
-extern void bpf_asm_compile(FILE *fp, bool cstyle);
-static void bpf_set_curr_instr(uint16_t op, uint8_t jt, uint8_t jf, uint32_t k);
-static void bpf_set_curr_label(char *label);
-static void bpf_set_jmp_label(char *label, enum jmp_type type);
-
-%}
-
-%union {
-	char *label;
-	uint32_t number;
-}
-
-%token OP_LDB OP_LDH OP_LD OP_LDX OP_ST OP_STX OP_JMP OP_JEQ OP_JGT OP_JGE
-%token OP_JSET OP_ADD OP_SUB OP_MUL OP_DIV OP_AND OP_OR OP_XOR OP_LSH OP_RSH
-%token OP_RET OP_TAX OP_TXA OP_LDXB OP_MOD OP_NEG OP_JNEQ OP_JLT OP_JLE OP_LDI
-%token OP_LDXI
-
-%token K_PKT_LEN
-
-%token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%'
-
-%token extension number label
-
-%type <label> label
-%type <number> extension
-%type <number> number
-
-%%
-
-prog
-	: line
-	| prog line
-	;
-
-line
-	: instr
-	| labelled_instr
-	;
-
-labelled_instr
-	: labelled instr
-	;
-
-instr
-	: ldb
-	| ldh
-	| ld
-	| ldi
-	| ldx
-	| ldxi
-	| st
-	| stx
-	| jmp
-	| jeq
-	| jneq
-	| jlt
-	| jle
-	| jgt
-	| jge
-	| jset
-	| add
-	| sub
-	| mul
-	| div
-	| mod
-	| neg
-	| and
-	| or
-	| xor
-	| lsh
-	| rsh
-	| ret
-	| tax
-	| txa
-	;
-
-labelled
-	: label ':' { bpf_set_curr_label($1); }
-	;
-
-ldb
-	: OP_LDB '[' 'x' '+' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $5); }
-	| OP_LDB '[' '%' 'x' '+' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $6); }
-	| OP_LDB '[' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, $3); }
-	| OP_LDB extension {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + $2); }
-	;
-
-ldh
-	: OP_LDH '[' 'x' '+' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $5); }
-	| OP_LDH '[' '%' 'x' '+' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $6); }
-	| OP_LDH '[' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, $3); }
-	| OP_LDH extension {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + $2); }
-	;
-
-ldi
-	: OP_LDI '#' number {
-		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
-	| OP_LDI number {
-		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $2); }
-	;
-
-ld
-	: OP_LD '#' number {
-		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
-	| OP_LD K_PKT_LEN {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_LEN, 0, 0, 0); }
-	| OP_LD extension {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + $2); }
-	| OP_LD 'M' '[' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); }
-	| OP_LD '[' 'x' '+' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $5); }
-	| OP_LD '[' '%' 'x' '+' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $6); }
-	| OP_LD '[' number ']' {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, $3); }
-	;
-
-ldxi
-	: OP_LDXI '#' number {
-		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
-	| OP_LDXI number {
-		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $2); }
-	;
-
-ldx
-	: OP_LDX '#' number {
-		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
-	| OP_LDX K_PKT_LEN {
-		bpf_set_curr_instr(BPF_LDX | BPF_W | BPF_LEN, 0, 0, 0); }
-	| OP_LDX 'M' '[' number ']' {
-		bpf_set_curr_instr(BPF_LDX | BPF_MEM, 0, 0, $4); }
-	| OP_LDXB number '*' '(' '[' number ']' '&' number ')' {
-		if ($2 != 4 || $9 != 0xf) {
-			fprintf(stderr, "ldxb offset not supported!\n");
-			exit(0);
-		} else {
-			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
-	| OP_LDX number '*' '(' '[' number ']' '&' number ')' {
-		if ($2 != 4 || $9 != 0xf) {
-			fprintf(stderr, "ldxb offset not supported!\n");
-			exit(0);
-		} else {
-			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
-	;
-
-st
-	: OP_ST 'M' '[' number ']' {
-		bpf_set_curr_instr(BPF_ST, 0, 0, $4); }
-	;
-
-stx
-	: OP_STX 'M' '[' number ']' {
-		bpf_set_curr_instr(BPF_STX, 0, 0, $4); }
-	;
-
-jmp
-	: OP_JMP label {
-		bpf_set_jmp_label($2, JKL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JA, 0, 0, 0); }
-	;
-
-jeq
-	: OP_JEQ '#' number ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
-	| OP_JEQ 'x' ',' label ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_jmp_label($6, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
-	| OP_JEQ '%' 'x' ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
-	| OP_JEQ '#' number ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
-	| OP_JEQ 'x' ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
-	| OP_JEQ '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
-	;
-
-jneq
-	: OP_JNEQ '#' number ',' label {
-		bpf_set_jmp_label($5, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
-	| OP_JNEQ 'x' ',' label {
-		bpf_set_jmp_label($4, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
-	| OP_JNEQ '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
-	;
-
-jlt
-	: OP_JLT '#' number ',' label {
-		bpf_set_jmp_label($5, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
-	| OP_JLT 'x' ',' label {
-		bpf_set_jmp_label($4, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
-	| OP_JLT '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
-	;
-
-jle
-	: OP_JLE '#' number ',' label {
-		bpf_set_jmp_label($5, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
-	| OP_JLE 'x' ',' label {
-		bpf_set_jmp_label($4, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
-	| OP_JLE '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
-	;
-
-jgt
-	: OP_JGT '#' number ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
-	| OP_JGT 'x' ',' label ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_jmp_label($6, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
-	| OP_JGT '%' 'x' ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
-	| OP_JGT '#' number ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
-	| OP_JGT 'x' ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
-	| OP_JGT '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
-	;
-
-jge
-	: OP_JGE '#' number ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
-	| OP_JGE 'x' ',' label ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_jmp_label($6, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
-	| OP_JGE '%' 'x' ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
-	| OP_JGE '#' number ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
-	| OP_JGE 'x' ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
-	| OP_JGE '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
-	;
-
-jset
-	: OP_JSET '#' number ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
-	| OP_JSET 'x' ',' label ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_jmp_label($6, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
-	| OP_JSET '%' 'x' ',' label ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_jmp_label($7, JFL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
-	| OP_JSET '#' number ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
-	| OP_JSET 'x' ',' label {
-		bpf_set_jmp_label($4, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
-	| OP_JSET '%' 'x' ',' label {
-		bpf_set_jmp_label($5, JTL);
-		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
-	;
-
-add
-	: OP_ADD '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_K, 0, 0, $3); }
-	| OP_ADD 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
-	| OP_ADD '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
-	;
-
-sub
-	: OP_SUB '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_K, 0, 0, $3); }
-	| OP_SUB 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
-	| OP_SUB '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
-	;
-
-mul
-	: OP_MUL '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_K, 0, 0, $3); }
-	| OP_MUL 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
-	| OP_MUL '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
-	;
-
-div
-	: OP_DIV '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_K, 0, 0, $3); }
-	| OP_DIV 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
-	| OP_DIV '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
-	;
-
-mod
-	: OP_MOD '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_K, 0, 0, $3); }
-	| OP_MOD 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
-	| OP_MOD '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
-	;
-
-neg
-	: OP_NEG {
-		bpf_set_curr_instr(BPF_ALU | BPF_NEG, 0, 0, 0); }
-	;
-
-and
-	: OP_AND '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_K, 0, 0, $3); }
-	| OP_AND 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
-	| OP_AND '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
-	;
-
-or
-	: OP_OR '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_K, 0, 0, $3); }
-	| OP_OR 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
-	| OP_OR '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
-	;
-
-xor
-	: OP_XOR '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_K, 0, 0, $3); }
-	| OP_XOR 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
-	| OP_XOR '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
-	;
-
-lsh
-	: OP_LSH '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_K, 0, 0, $3); }
-	| OP_LSH 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
-	| OP_LSH '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
-	;
-
-rsh
-	: OP_RSH '#' number {
-		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_K, 0, 0, $3); }
-	| OP_RSH 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
-	| OP_RSH '%' 'x' {
-		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
-	;
-
-ret
-	: OP_RET 'a' {
-		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
-	| OP_RET '%' 'a' {
-		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
-	| OP_RET 'x' {
-		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
-	| OP_RET '%' 'x' {
-		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
-	| OP_RET '#' number {
-		bpf_set_curr_instr(BPF_RET | BPF_K, 0, 0, $3); }
-	;
-
-tax
-	: OP_TAX {
-		bpf_set_curr_instr(BPF_MISC | BPF_TAX, 0, 0, 0); }
-	;
-
-txa
-	: OP_TXA {
-		bpf_set_curr_instr(BPF_MISC | BPF_TXA, 0, 0, 0); }
-	;
-
-%%
-
-static int curr_instr = 0;
-static struct sock_filter out[BPF_MAXINSNS];
-static char **labels, **labels_jt, **labels_jf, **labels_k;
-
-static void bpf_assert_max(void)
-{
-	if (curr_instr >= BPF_MAXINSNS) {
-		fprintf(stderr, "only max %u insns allowed!\n", BPF_MAXINSNS);
-		exit(0);
-	}
-}
-
-static void bpf_set_curr_instr(uint16_t code, uint8_t jt, uint8_t jf,
-			       uint32_t k)
-{
-	bpf_assert_max();
-	out[curr_instr].code = code;
-	out[curr_instr].jt = jt;
-	out[curr_instr].jf = jf;
-	out[curr_instr].k = k;
-	curr_instr++;
-}
-
-static void bpf_set_curr_label(char *label)
-{
-	bpf_assert_max();
-	labels[curr_instr] = label;
-}
-
-static void bpf_set_jmp_label(char *label, enum jmp_type type)
-{
-	bpf_assert_max();
-	switch (type) {
-	case JTL:
-		labels_jt[curr_instr] = label;
-		break;
-	case JFL:
-		labels_jf[curr_instr] = label;
-		break;
-	case JKL:
-		labels_k[curr_instr] = label;
-		break;
-	}
-}
-
-static int bpf_find_insns_offset(const char *label)
-{
-	int i, max = curr_instr, ret = -ENOENT;
-
-	for (i = 0; i < max; i++) {
-		if (labels[i] && !strcmp(label, labels[i])) {
-			ret = i;
-			break;
-		}
-	}
-
-	if (ret == -ENOENT) {
-		fprintf(stderr, "no such label \'%s\'!\n", label);
-		exit(0);
-	}
-
-	return ret;
-}
-
-static void bpf_stage_1_insert_insns(void)
-{
-	yyparse();
-}
-
-static void bpf_reduce_k_jumps(void)
-{
-	int i;
-
-	for (i = 0; i < curr_instr; i++) {
-		if (labels_k[i]) {
-			int off = bpf_find_insns_offset(labels_k[i]);
-			out[i].k = (uint32_t) (off - i - 1);
-		}
-	}
-}
-
-static void bpf_reduce_jt_jumps(void)
-{
-	int i;
-
-	for (i = 0; i < curr_instr; i++) {
-		if (labels_jt[i]) {
-			int off = bpf_find_insns_offset(labels_jt[i]);
-			out[i].jt = (uint8_t) (off - i -1);
-		}
-	}
-}
-
-static void bpf_reduce_jf_jumps(void)
-{
-	int i;
-
-	for (i = 0; i < curr_instr; i++) {
-		if (labels_jf[i]) {
-			int off = bpf_find_insns_offset(labels_jf[i]);
-			out[i].jf = (uint8_t) (off - i - 1);
-		}
-	}
-}
-
-static void bpf_stage_2_reduce_labels(void)
-{
-	bpf_reduce_k_jumps();
-	bpf_reduce_jt_jumps();
-	bpf_reduce_jf_jumps();
-}
-
-static void bpf_pretty_print_c(void)
-{
-	int i;
-
-	for (i = 0; i < curr_instr; i++)
-		printf("{ %#04x, %2u, %2u, %#010x },\n", out[i].code,
-		       out[i].jt, out[i].jf, out[i].k);
-}
-
-static void bpf_pretty_print(void)
-{
-	int i;
-
-	printf("%u,", curr_instr);
-	for (i = 0; i < curr_instr; i++)
-		printf("%u %u %u %u,", out[i].code,
-		       out[i].jt, out[i].jf, out[i].k);
-	printf("\n");
-}
-
-static void bpf_init(void)
-{
-	memset(out, 0, sizeof(out));
-
-	labels = calloc(BPF_MAXINSNS, sizeof(*labels));
-	assert(labels);
-	labels_jt = calloc(BPF_MAXINSNS, sizeof(*labels_jt));
-	assert(labels_jt);
-	labels_jf = calloc(BPF_MAXINSNS, sizeof(*labels_jf));
-	assert(labels_jf);
-	labels_k = calloc(BPF_MAXINSNS, sizeof(*labels_k));
-	assert(labels_k);
-}
-
-static void bpf_destroy_labels(void)
-{
-	int i;
-
-	for (i = 0; i < curr_instr; i++) {
-		free(labels_jf[i]);
-		free(labels_jt[i]);
-		free(labels_k[i]);
-		free(labels[i]);
-	}
-}
-
-static void bpf_destroy(void)
-{
-	bpf_destroy_labels();
-	free(labels_jt);
-	free(labels_jf);
-	free(labels_k);
-	free(labels);
-}
-
-void bpf_asm_compile(FILE *fp, bool cstyle)
-{
-	yyin = fp;
-
-	bpf_init();
-	bpf_stage_1_insert_insns();
-	bpf_stage_2_reduce_labels();
-	bpf_destroy();
-
-	if (cstyle)
-		bpf_pretty_print_c();
-	else
-		bpf_pretty_print();
-
-	if (fp != stdin)
-		fclose(yyin);
-}
-
-void yyerror(const char *str)
-{
-	fprintf(stderr, "error: %s at line %d\n", str, yylineno);
-	exit(1);
-}
diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
deleted file mode 100644
index 422d9abd666a..000000000000
--- a/tools/net/bpf_jit_disasm.c
+++ /dev/null
@@ -1,320 +0,0 @@
-/*
- * Minimal BPF JIT image disassembler
- *
- * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for
- * debugging or verification purposes.
- *
- * To get the disassembly of the JIT code, do the following:
- *
- *  1) `echo 2 > /proc/sys/net/core/bpf_jit_enable`
- *  2) Load a BPF filter (e.g. `tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24`)
- *  3) Run e.g. `bpf_jit_disasm -o` to read out the last JIT code
- *
- * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <assert.h>
-#include <unistd.h>
-#include <string.h>
-#include <bfd.h>
-#include <dis-asm.h>
-#include <regex.h>
-#include <fcntl.h>
-#include <sys/klog.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#define CMD_ACTION_SIZE_BUFFER		10
-#define CMD_ACTION_READ_ALL		3
-
-static void get_exec_path(char *tpath, size_t size)
-{
-	char *path;
-	ssize_t len;
-
-	snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
-	tpath[size - 1] = 0;
-
-	path = strdup(tpath);
-	assert(path);
-
-	len = readlink(path, tpath, size);
-	tpath[len] = 0;
-
-	free(path);
-}
-
-static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
-{
-	int count, i, pc = 0;
-	char tpath[256];
-	struct disassemble_info info;
-	disassembler_ftype disassemble;
-	bfd *bfdf;
-
-	memset(tpath, 0, sizeof(tpath));
-	get_exec_path(tpath, sizeof(tpath));
-
-	bfdf = bfd_openr(tpath, NULL);
-	assert(bfdf);
-	assert(bfd_check_format(bfdf, bfd_object));
-
-	init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf);
-	info.arch = bfd_get_arch(bfdf);
-	info.mach = bfd_get_mach(bfdf);
-	info.buffer = image;
-	info.buffer_length = len;
-
-	disassemble_init_for_target(&info);
-
-	disassemble = disassembler(bfdf);
-	assert(disassemble);
-
-	do {
-		printf("%4x:\t", pc);
-
-		count = disassemble(pc, &info);
-
-		if (opcodes) {
-			printf("\n\t");
-			for (i = 0; i < count; ++i)
-				printf("%02x ", (uint8_t) image[pc + i]);
-		}
-		printf("\n");
-
-		pc += count;
-	} while(count > 0 && pc < len);
-
-	bfd_close(bfdf);
-}
-
-static char *get_klog_buff(unsigned int *klen)
-{
-	int ret, len;
-	char *buff;
-
-	len = klogctl(CMD_ACTION_SIZE_BUFFER, NULL, 0);
-	if (len < 0)
-		return NULL;
-
-	buff = malloc(len);
-	if (!buff)
-		return NULL;
-
-	ret = klogctl(CMD_ACTION_READ_ALL, buff, len);
-	if (ret < 0) {
-		free(buff);
-		return NULL;
-	}
-
-	*klen = ret;
-	return buff;
-}
-
-static char *get_flog_buff(const char *file, unsigned int *klen)
-{
-	int fd, ret, len;
-	struct stat fi;
-	char *buff;
-
-	fd = open(file, O_RDONLY);
-	if (fd < 0)
-		return NULL;
-
-	ret = fstat(fd, &fi);
-	if (ret < 0 || !S_ISREG(fi.st_mode))
-		goto out;
-
-	len = fi.st_size + 1;
-	buff = malloc(len);
-	if (!buff)
-		goto out;
-
-	memset(buff, 0, len);
-	ret = read(fd, buff, len - 1);
-	if (ret <= 0)
-		goto out_free;
-
-	close(fd);
-	*klen = ret;
-	return buff;
-out_free:
-	free(buff);
-out:
-	close(fd);
-	return NULL;
-}
-
-static char *get_log_buff(const char *file, unsigned int *klen)
-{
-	return file ? get_flog_buff(file, klen) : get_klog_buff(klen);
-}
-
-static void put_log_buff(char *buff)
-{
-	free(buff);
-}
-
-static uint8_t *get_last_jit_image(char *haystack, size_t hlen,
-				   unsigned int *ilen)
-{
-	char *ptr, *pptr, *tmp;
-	off_t off = 0;
-	int ret, flen, proglen, pass, ulen = 0;
-	regmatch_t pmatch[1];
-	unsigned long base;
-	regex_t regex;
-	uint8_t *image;
-
-	if (hlen == 0)
-		return NULL;
-
-	ret = regcomp(&regex, "flen=[[:alnum:]]+ proglen=[[:digit:]]+ "
-		      "pass=[[:digit:]]+ image=[[:xdigit:]]+", REG_EXTENDED);
-	assert(ret == 0);
-
-	ptr = haystack;
-	memset(pmatch, 0, sizeof(pmatch));
-
-	while (1) {
-		ret = regexec(&regex, ptr, 1, pmatch, 0);
-		if (ret == 0) {
-			ptr += pmatch[0].rm_eo;
-			off += pmatch[0].rm_eo;
-			assert(off < hlen);
-		} else
-			break;
-	}
-
-	ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so);
-	ret = sscanf(ptr, "flen=%d proglen=%d pass=%d image=%lx",
-		     &flen, &proglen, &pass, &base);
-	if (ret != 4) {
-		regfree(&regex);
-		return NULL;
-	}
-	if (proglen > 1000000) {
-		printf("proglen of %d too big, stopping\n", proglen);
-		return NULL;
-	}
-
-	image = malloc(proglen);
-	if (!image) {
-		printf("Out of memory\n");
-		return NULL;
-	}
-	memset(image, 0, proglen);
-
-	tmp = ptr = haystack + off;
-	while ((ptr = strtok(tmp, "\n")) != NULL && ulen < proglen) {
-		tmp = NULL;
-		if (!strstr(ptr, "JIT code"))
-			continue;
-		pptr = ptr;
-		while ((ptr = strstr(pptr, ":")))
-			pptr = ptr + 1;
-		ptr = pptr;
-		do {
-			image[ulen++] = (uint8_t) strtoul(pptr, &pptr, 16);
-			if (ptr == pptr) {
-				ulen--;
-				break;
-			}
-			if (ulen >= proglen)
-				break;
-			ptr = pptr;
-		} while (1);
-	}
-
-	assert(ulen == proglen);
-	printf("%d bytes emitted from JIT compiler (pass:%d, flen:%d)\n",
-	       proglen, pass, flen);
-	printf("%lx + <x>:\n", base);
-
-	regfree(&regex);
-	*ilen = ulen;
-	return image;
-}
-
-static void usage(void)
-{
-	printf("Usage: bpf_jit_disasm [...]\n");
-	printf("       -o          Also display related opcodes (default: off).\n");
-	printf("       -O <file>   Write binary image of code to file, don't disassemble to stdout.\n");
-	printf("       -f <file>   Read last image dump from file or stdin (default: klog).\n");
-	printf("       -h          Display this help.\n");
-}
-
-int main(int argc, char **argv)
-{
-	unsigned int len, klen, opt, opcodes = 0;
-	char *kbuff, *file = NULL;
-	char *ofile = NULL;
-	int ofd;
-	ssize_t nr;
-	uint8_t *pos;
-	uint8_t *image = NULL;
-
-	while ((opt = getopt(argc, argv, "of:O:")) != -1) {
-		switch (opt) {
-		case 'o':
-			opcodes = 1;
-			break;
-		case 'O':
-			ofile = optarg;
-			break;
-		case 'f':
-			file = optarg;
-			break;
-		default:
-			usage();
-			return -1;
-		}
-	}
-
-	bfd_init();
-
-	kbuff = get_log_buff(file, &klen);
-	if (!kbuff) {
-		fprintf(stderr, "Could not retrieve log buffer!\n");
-		return -1;
-	}
-
-	image = get_last_jit_image(kbuff, klen, &len);
-	if (!image) {
-		fprintf(stderr, "No JIT image found!\n");
-		goto done;
-	}
-	if (!ofile) {
-		get_asm_insns(image, len, opcodes);
-		goto done;
-	}
-
-	ofd = open(ofile, O_WRONLY | O_CREAT | O_TRUNC, DEFFILEMODE);
-	if (ofd < 0) {
-		fprintf(stderr, "Could not open file %s for writing: ", ofile);
-		perror(NULL);
-		goto done;
-	}
-	pos = image;
-	do {
-		nr = write(ofd, pos, len);
-		if (nr < 0) {
-			fprintf(stderr, "Could not write data to %s: ", ofile);
-			perror(NULL);
-			goto done;
-		}
-		len -= nr;
-		pos += nr;
-	} while (len);
-	close(ofd);
-
-done:
-	put_log_buff(kbuff);
-	free(image);
-	return 0;
-}
-- 
cgit v1.2.3


From 71bb428fe2c19512ac671d5ee16ef3e73e1b49a8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 4 Oct 2017 20:10:04 -0700
Subject: tools: bpf: add bpftool

Add a simple tool for querying and updating BPF objects on the system.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/Makefile             |  18 +-
 tools/bpf/bpftool/Makefile     |  80 +++++
 tools/bpf/bpftool/common.c     | 216 ++++++++++++
 tools/bpf/bpftool/jit_disasm.c |  87 +++++
 tools/bpf/bpftool/main.c       | 212 ++++++++++++
 tools/bpf/bpftool/main.h       |  99 ++++++
 tools/bpf/bpftool/map.c        | 744 +++++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/prog.c       | 456 +++++++++++++++++++++++++
 8 files changed, 1909 insertions(+), 3 deletions(-)
 create mode 100644 tools/bpf/bpftool/Makefile
 create mode 100644 tools/bpf/bpftool/common.c
 create mode 100644 tools/bpf/bpftool/jit_disasm.c
 create mode 100644 tools/bpf/bpftool/main.c
 create mode 100644 tools/bpf/bpftool/main.h
 create mode 100644 tools/bpf/bpftool/map.c
 create mode 100644 tools/bpf/bpftool/prog.c

(limited to 'tools')

diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index ddf888010652..325a35e1c28e 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -3,6 +3,7 @@ prefix = /usr
 CC = gcc
 LEX = flex
 YACC = bison
+MAKE = make
 
 CFLAGS += -Wall -O2
 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
@@ -13,7 +14,7 @@ CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
 %.lex.c: %.l
 	$(LEX) -o $@ $<
 
-all : bpf_jit_disasm bpf_dbg bpf_asm
+all: bpf_jit_disasm bpf_dbg bpf_asm bpftool
 
 bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
@@ -26,10 +27,21 @@ bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
 
-clean :
+clean: bpftool_clean
 	rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
 
-install :
+install: bpftool_install
 	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
 	install bpf_dbg $(prefix)/bin/bpf_dbg
 	install bpf_asm $(prefix)/bin/bpf_asm
+
+bpftool:
+	$(MAKE) -C bpftool
+
+bpftool_install:
+	$(MAKE) -C bpftool install
+
+bpftool_clean:
+	$(MAKE) -C bpftool clean
+
+.PHONY: bpftool FORCE
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
new file mode 100644
index 000000000000..a7151f47fb40
--- /dev/null
+++ b/tools/bpf/bpftool/Makefile
@@ -0,0 +1,80 @@
+include ../../scripts/Makefile.include
+
+include ../../scripts/utilities.mak
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+# Adding $(OUTPUT) as a directory to look for source files,
+# because use generated output files as sources dependency
+# for flex/bison parsers.
+VPATH += $(OUTPUT)
+export VPATH
+endif
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+BPF_DIR	= $(srctree)/tools/lib/bpf/
+
+ifneq ($(OUTPUT),)
+  BPF_PATH=$(OUTPUT)
+else
+  BPF_PATH=$(BPF_DIR)
+endif
+
+LIBBPF = $(BPF_PATH)libbpf.a
+
+$(LIBBPF): FORCE
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
+
+$(LIBBPF)-clean:
+	$(call QUIET_CLEAN, libbpf)
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null
+
+prefix = /usr
+
+CC = gcc
+
+CFLAGS += -O2
+CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow
+CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf
+LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
+
+include $(wildcard *.d)
+
+all: $(OUTPUT)bpftool
+
+SRCS=$(wildcard *.c)
+OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS))
+
+$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
+	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS)
+
+$(OUTPUT)%.o: %.c
+	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
+
+clean: $(LIBBPF)-clean
+	$(call QUIET_CLEAN, bpftool)
+	$(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
+
+install:
+	install $(OUTPUT)bpftool $(prefix)/sbin/bpftool
+
+FORCE:
+
+.PHONY: all clean FORCE
+.DEFAULT_GOAL := all
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
new file mode 100644
index 000000000000..df8396a0c400
--- /dev/null
+++ b/tools/bpf/bpftool/common.c
@@ -0,0 +1,216 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <errno.h>
+#include <libgen.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/limits.h>
+#include <linux/magic.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+static bool is_bpffs(char *path)
+{
+	struct statfs st_fs;
+
+	if (statfs(path, &st_fs) < 0)
+		return false;
+
+	return (unsigned long)st_fs.f_type == BPF_FS_MAGIC;
+}
+
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
+{
+	enum bpf_obj_type type;
+	int fd;
+
+	fd = bpf_obj_get(path);
+	if (fd < 0) {
+		err("bpf obj get (%s): %s\n", path,
+		    errno == EACCES && !is_bpffs(dirname(path)) ?
+		    "directory not in bpf file system (bpffs)" :
+		    strerror(errno));
+		return -1;
+	}
+
+	type = get_fd_type(fd);
+	if (type < 0) {
+		close(fd);
+		return type;
+	}
+	if (type != exp_type) {
+		err("incorrect object type: %s\n", get_fd_type_name(type));
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
+{
+	unsigned int id;
+	char *endptr;
+	int err;
+	int fd;
+
+	if (!is_prefix(*argv, "id")) {
+		err("expected 'id' got %s\n", *argv);
+		return -1;
+	}
+	NEXT_ARG();
+
+	id = strtoul(*argv, &endptr, 0);
+	if (*endptr) {
+		err("can't parse %s as ID\n", *argv);
+		return -1;
+	}
+	NEXT_ARG();
+
+	if (argc != 1)
+		usage();
+
+	fd = get_fd_by_id(id);
+	if (fd < 0) {
+		err("can't get prog by id (%u): %s\n", id, strerror(errno));
+		return -1;
+	}
+
+	err = bpf_obj_pin(fd, *argv);
+	close(fd);
+	if (err) {
+		err("can't pin the object (%s): %s\n", *argv,
+		    errno == EACCES && !is_bpffs(dirname(*argv)) ?
+		    "directory not in bpf file system (bpffs)" :
+		    strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+const char *get_fd_type_name(enum bpf_obj_type type)
+{
+	static const char * const names[] = {
+		[BPF_OBJ_UNKNOWN]	= "unknown",
+		[BPF_OBJ_PROG]		= "prog",
+		[BPF_OBJ_MAP]		= "map",
+	};
+
+	if (type < 0 || type >= ARRAY_SIZE(names) || !names[type])
+		return names[BPF_OBJ_UNKNOWN];
+
+	return names[type];
+}
+
+int get_fd_type(int fd)
+{
+	char path[PATH_MAX];
+	char buf[512];
+	ssize_t n;
+
+	snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd);
+
+	n = readlink(path, buf, sizeof(buf));
+	if (n < 0) {
+		err("can't read link type: %s\n", strerror(errno));
+		return -1;
+	}
+	if (n == sizeof(path)) {
+		err("can't read link type: path too long!\n");
+		return -1;
+	}
+
+	if (strstr(buf, "bpf-map"))
+		return BPF_OBJ_MAP;
+	else if (strstr(buf, "bpf-prog"))
+		return BPF_OBJ_PROG;
+
+	return BPF_OBJ_UNKNOWN;
+}
+
+char *get_fdinfo(int fd, const char *key)
+{
+	char path[PATH_MAX];
+	char *line = NULL;
+	size_t line_n = 0;
+	ssize_t n;
+	FILE *fdi;
+
+	snprintf(path, sizeof(path), "/proc/%d/fdinfo/%d", getpid(), fd);
+
+	fdi = fopen(path, "r");
+	if (!fdi) {
+		err("can't open fdinfo: %s\n", strerror(errno));
+		return NULL;
+	}
+
+	while ((n = getline(&line, &line_n, fdi))) {
+		char *value;
+		int len;
+
+		if (!strstr(line, key))
+			continue;
+
+		fclose(fdi);
+
+		value = strchr(line, '\t');
+		if (!value || !value[1]) {
+			err("malformed fdinfo!?\n");
+			free(line);
+			return NULL;
+		}
+		value++;
+
+		len = strlen(value);
+		memmove(line, value, len);
+		line[len - 1] = '\0';
+
+		return line;
+	}
+
+	err("key '%s' not found in fdinfo\n", key);
+	free(line);
+	fclose(fdi);
+	return NULL;
+}
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
new file mode 100644
index 000000000000..70e480b59e9d
--- /dev/null
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -0,0 +1,87 @@
+/*
+ * Based on:
+ *
+ * Minimal BPF JIT image disassembler
+ *
+ * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for
+ * debugging or verification purposes.
+ *
+ * Copyright 2013 Daniel Borkmann <daniel@iogearbox.net>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+#include <bfd.h>
+#include <dis-asm.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+static void get_exec_path(char *tpath, size_t size)
+{
+	ssize_t len;
+	char *path;
+
+	snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
+	tpath[size - 1] = 0;
+
+	path = strdup(tpath);
+	assert(path);
+
+	len = readlink(path, tpath, size - 1);
+	assert(len > 0);
+	tpath[len] = 0;
+
+	free(path);
+}
+
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
+{
+	disassembler_ftype disassemble;
+	struct disassemble_info info;
+	int count, i, pc = 0;
+	char tpath[256];
+	bfd *bfdf;
+
+	if (!len)
+		return;
+
+	memset(tpath, 0, sizeof(tpath));
+	get_exec_path(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	assert(bfdf);
+	assert(bfd_check_format(bfdf, bfd_object));
+
+	init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf);
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+	info.buffer = image;
+	info.buffer_length = len;
+
+	disassemble_init_for_target(&info);
+
+	disassemble = disassembler(bfdf);
+	assert(disassemble);
+
+	do {
+		printf("%4x:\t", pc);
+
+		count = disassemble(pc, &info);
+
+		if (opcodes) {
+			printf("\n\t");
+			for (i = 0; i < count; ++i)
+				printf("%02x ", (uint8_t) image[pc + i]);
+		}
+		printf("\n");
+
+		pc += count;
+	} while (count > 0 && pc < len);
+
+	bfd_close(bfdf);
+}
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
new file mode 100644
index 000000000000..e02d00d6e00b
--- /dev/null
+++ b/tools/bpf/bpftool/main.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <bfd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <linux/bpf.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+const char *bin_name;
+static int last_argc;
+static char **last_argv;
+static int (*last_do_help)(int argc, char **argv);
+
+void usage(void)
+{
+	last_do_help(last_argc - 1, last_argv + 1);
+
+	exit(-1);
+}
+
+static int do_help(int argc, char **argv)
+{
+	fprintf(stderr,
+		"Usage: %s OBJECT { COMMAND | help }\n"
+		"       %s batch file FILE\n"
+		"\n"
+		"       OBJECT := { prog | map }\n",
+		bin_name, bin_name);
+
+	return 0;
+}
+
+int cmd_select(const struct cmd *cmds, int argc, char **argv,
+	       int (*help)(int argc, char **argv))
+{
+	unsigned int i;
+
+	last_argc = argc;
+	last_argv = argv;
+	last_do_help = help;
+
+	if (argc < 1 && cmds[0].func)
+		return cmds[0].func(argc, argv);
+
+	for (i = 0; cmds[i].func; i++)
+		if (is_prefix(*argv, cmds[i].cmd))
+			return cmds[i].func(argc - 1, argv + 1);
+
+	help(argc - 1, argv + 1);
+
+	return -1;
+}
+
+bool is_prefix(const char *pfx, const char *str)
+{
+	if (!pfx)
+		return false;
+	if (strlen(str) < strlen(pfx))
+		return false;
+
+	return !memcmp(str, pfx, strlen(pfx));
+}
+
+void print_hex(void *arg, unsigned int n, const char *sep)
+{
+	unsigned char *data = arg;
+	unsigned int i;
+
+	for (i = 0; i < n; i++) {
+		const char *pfx = "";
+
+		if (!i)
+			/* nothing */;
+		else if (!(i % 16))
+			printf("\n");
+		else if (!(i % 8))
+			printf("  ");
+		else
+			pfx = sep;
+
+		printf("%s%02hhx", i ? pfx : "", data[i]);
+	}
+}
+
+static int do_batch(int argc, char **argv);
+
+static const struct cmd cmds[] = {
+	{ "help",	do_help },
+	{ "batch",	do_batch },
+	{ "prog",	do_prog },
+	{ "map",	do_map },
+	{ 0 }
+};
+
+static int do_batch(int argc, char **argv)
+{
+	unsigned int lines = 0;
+	char *n_argv[4096];
+	char buf[65536];
+	int n_argc;
+	FILE *fp;
+	int err;
+
+	if (argc < 2) {
+		err("too few parameters for batch\n");
+		return -1;
+	} else if (!is_prefix(*argv, "file")) {
+		err("expected 'file', got: %s\n", *argv);
+		return -1;
+	} else if (argc > 2) {
+		err("too many parameters for batch\n");
+		return -1;
+	}
+	NEXT_ARG();
+
+	fp = fopen(*argv, "r");
+	if (!fp) {
+		err("Can't open file (%s): %s\n", *argv, strerror(errno));
+		return -1;
+	}
+
+	while (fgets(buf, sizeof(buf), fp)) {
+		if (strlen(buf) == sizeof(buf) - 1) {
+			errno = E2BIG;
+			break;
+		}
+
+		n_argc = 0;
+		n_argv[n_argc] = strtok(buf, " \t\n");
+
+		while (n_argv[n_argc]) {
+			n_argc++;
+			if (n_argc == ARRAY_SIZE(n_argv)) {
+				err("line %d has too many arguments, skip\n",
+				    lines);
+				n_argc = 0;
+				break;
+			}
+			n_argv[n_argc] = strtok(NULL, " \t\n");
+		}
+
+		if (!n_argc)
+			continue;
+
+		err = cmd_select(cmds, n_argc, n_argv, do_help);
+		if (err)
+			goto err_close;
+
+		lines++;
+	}
+
+	if (errno && errno != ENOENT) {
+		perror("reading batch file failed");
+		err = -1;
+	} else {
+		info("processed %d lines\n", lines);
+		err = 0;
+	}
+err_close:
+	fclose(fp);
+
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	bin_name = argv[0];
+	NEXT_ARG();
+
+	bfd_init();
+
+	return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
new file mode 100644
index 000000000000..85d2d7870a58
--- /dev/null
+++ b/tools/bpf/bpftool/main.h
@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#ifndef __BPF_TOOL_H
+#define __BPF_TOOL_H
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <linux/bpf.h>
+
+#define ARRAY_SIZE(a)	(sizeof(a) / sizeof(a[0]))
+
+#define err(msg...)	fprintf(stderr, "Error: " msg)
+#define warn(msg...)	fprintf(stderr, "Warning: " msg)
+#define info(msg...)	fprintf(stderr, msg)
+
+#define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
+
+#define min(a, b)							\
+	({ typeof(a) _a = (a); typeof(b) _b = (b); _a > _b ? _b : _a; })
+#define max(a, b)							\
+	({ typeof(a) _a = (a); typeof(b) _b = (b); _a < _b ? _b : _a; })
+
+#define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
+#define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
+#define BAD_ARG()	({ err("what is '%s'?\n", *argv); -1; })
+
+#define BPF_TAG_FMT	"%02hhx:%02hhx:%02hhx:%02hhx:"	\
+			"%02hhx:%02hhx:%02hhx:%02hhx"
+
+#define HELP_SPEC_PROGRAM						\
+	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
+
+enum bpf_obj_type {
+	BPF_OBJ_UNKNOWN,
+	BPF_OBJ_PROG,
+	BPF_OBJ_MAP,
+};
+
+extern const char *bin_name;
+
+bool is_prefix(const char *pfx, const char *str);
+void print_hex(void *arg, unsigned int n, const char *sep);
+void usage(void) __attribute__((noreturn));
+
+struct cmd {
+	const char *cmd;
+	int (*func)(int argc, char **argv);
+};
+
+int cmd_select(const struct cmd *cmds, int argc, char **argv,
+	       int (*help)(int argc, char **argv));
+
+int get_fd_type(int fd);
+const char *get_fd_type_name(enum bpf_obj_type type);
+char *get_fdinfo(int fd, const char *key);
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
+
+int do_prog(int argc, char **arg);
+int do_map(int argc, char **arg);
+
+int prog_parse_fd(int *argc, char ***argv);
+
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
+
+#endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
new file mode 100644
index 000000000000..0528a5379e6c
--- /dev/null
+++ b/tools/bpf/bpftool/map.c
@@ -0,0 +1,744 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <assert.h>
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+static const char * const map_type_name[] = {
+	[BPF_MAP_TYPE_UNSPEC]		= "unspec",
+	[BPF_MAP_TYPE_HASH]		= "hash",
+	[BPF_MAP_TYPE_ARRAY]		= "array",
+	[BPF_MAP_TYPE_PROG_ARRAY]	= "prog_array",
+	[BPF_MAP_TYPE_PERF_EVENT_ARRAY]	= "perf_event_array",
+	[BPF_MAP_TYPE_PERCPU_HASH]	= "percpu_hash",
+	[BPF_MAP_TYPE_PERCPU_ARRAY]	= "percpu_array",
+	[BPF_MAP_TYPE_STACK_TRACE]	= "stack_trace",
+	[BPF_MAP_TYPE_CGROUP_ARRAY]	= "cgroup_array",
+	[BPF_MAP_TYPE_LRU_HASH]		= "lru_hash",
+	[BPF_MAP_TYPE_LRU_PERCPU_HASH]	= "lru_percpu_hash",
+	[BPF_MAP_TYPE_LPM_TRIE]		= "lpm_trie",
+	[BPF_MAP_TYPE_ARRAY_OF_MAPS]	= "array_of_maps",
+	[BPF_MAP_TYPE_HASH_OF_MAPS]	= "hash_of_maps",
+	[BPF_MAP_TYPE_DEVMAP]		= "devmap",
+	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
+};
+
+static unsigned int get_possible_cpus(void)
+{
+	static unsigned int result;
+	char buf[128];
+	long int n;
+	char *ptr;
+	int fd;
+
+	if (result)
+		return result;
+
+	fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
+	if (fd < 0) {
+		err("can't open sysfs possible cpus\n");
+		exit(-1);
+	}
+
+	n = read(fd, buf, sizeof(buf));
+	if (n < 2) {
+		err("can't read sysfs possible cpus\n");
+		exit(-1);
+	}
+	close(fd);
+
+	if (n == sizeof(buf)) {
+		err("read sysfs possible cpus overflow\n");
+		exit(-1);
+	}
+
+	ptr = buf;
+	n = 0;
+	while (*ptr && *ptr != '\n') {
+		unsigned int a, b;
+
+		if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
+			n += b - a + 1;
+
+			ptr = strchr(ptr, '-') + 1;
+		} else if (sscanf(ptr, "%u", &a) == 1) {
+			n++;
+		} else {
+			assert(0);
+		}
+
+		while (isdigit(*ptr))
+			ptr++;
+		if (*ptr == ',')
+			ptr++;
+	}
+
+	result = n;
+
+	return result;
+}
+
+static bool map_is_per_cpu(__u32 type)
+{
+	return type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+	       type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool map_is_map_of_maps(__u32 type)
+{
+	return type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+	       type == BPF_MAP_TYPE_HASH_OF_MAPS;
+}
+
+static bool map_is_map_of_progs(__u32 type)
+{
+	return type == BPF_MAP_TYPE_PROG_ARRAY;
+}
+
+static void *alloc_value(struct bpf_map_info *info)
+{
+	if (map_is_per_cpu(info->type))
+		return malloc(info->value_size * get_possible_cpus());
+	else
+		return malloc(info->value_size);
+}
+
+static int map_parse_fd(int *argc, char ***argv)
+{
+	int fd;
+
+	if (is_prefix(**argv, "id")) {
+		unsigned int id;
+		char *endptr;
+
+		NEXT_ARGP();
+
+		id = strtoul(**argv, &endptr, 0);
+		if (*endptr) {
+			err("can't parse %s as ID\n", **argv);
+			return -1;
+		}
+		NEXT_ARGP();
+
+		fd = bpf_map_get_fd_by_id(id);
+		if (fd < 0)
+			err("get map by id (%u): %s\n", id, strerror(errno));
+		return fd;
+	} else if (is_prefix(**argv, "pinned")) {
+		char *path;
+
+		NEXT_ARGP();
+
+		path = **argv;
+		NEXT_ARGP();
+
+		return open_obj_pinned_any(path, BPF_OBJ_MAP);
+	}
+
+	err("expected 'id' or 'pinned', got: '%s'?\n", **argv);
+	return -1;
+}
+
+static int
+map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
+{
+	int err;
+	int fd;
+
+	fd = map_parse_fd(argc, argv);
+	if (fd < 0)
+		return -1;
+
+	err = bpf_obj_get_info_by_fd(fd, info, info_len);
+	if (err) {
+		err("can't get map info: %s\n", strerror(errno));
+		close(fd);
+		return err;
+	}
+
+	return fd;
+}
+
+static void print_entry(struct bpf_map_info *info, unsigned char *key,
+			unsigned char *value)
+{
+	if (!map_is_per_cpu(info->type)) {
+		bool single_line, break_names;
+
+		break_names = info->key_size > 16 || info->value_size > 16;
+		single_line = info->key_size + info->value_size <= 24 &&
+			!break_names;
+
+		printf("key:%c", break_names ? '\n' : ' ');
+		print_hex(key, info->key_size, " ");
+
+		printf(single_line ? "  " : "\n");
+
+		printf("value:%c", break_names ? '\n' : ' ');
+		print_hex(value, info->value_size, " ");
+
+		printf("\n");
+	} else {
+		unsigned int i, n;
+
+		n = get_possible_cpus();
+
+		printf("key:\n");
+		print_hex(key, info->key_size, " ");
+		printf("\n");
+		for (i = 0; i < n; i++) {
+			printf("value (CPU %02d):%c",
+			       i, info->value_size > 16 ? '\n' : ' ');
+			print_hex(value + i * info->value_size,
+				  info->value_size, " ");
+			printf("\n");
+		}
+	}
+}
+
+static char **parse_bytes(char **argv, const char *name, unsigned char *val,
+			  unsigned int n)
+{
+	unsigned int i = 0;
+	char *endptr;
+
+	while (i < n && argv[i]) {
+		val[i] = strtoul(argv[i], &endptr, 0);
+		if (*endptr) {
+			err("error parsing byte: %s\n", argv[i]);
+			break;
+		}
+		i++;
+	}
+
+	if (i != n) {
+		err("%s expected %d bytes got %d\n", name, n, i);
+		return NULL;
+	}
+
+	return argv + i;
+}
+
+static int parse_elem(char **argv, struct bpf_map_info *info,
+		      void *key, void *value, __u32 key_size, __u32 value_size,
+		      __u32 *flags, __u32 **value_fd)
+{
+	if (!*argv) {
+		if (!key && !value)
+			return 0;
+		err("did not find %s\n", key ? "key" : "value");
+		return -1;
+	}
+
+	if (is_prefix(*argv, "key")) {
+		if (!key) {
+			if (key_size)
+				err("duplicate key\n");
+			else
+				err("unnecessary key\n");
+			return -1;
+		}
+
+		argv = parse_bytes(argv + 1, "key", key, key_size);
+		if (!argv)
+			return -1;
+
+		return parse_elem(argv, info, NULL, value, key_size, value_size,
+				  flags, value_fd);
+	} else if (is_prefix(*argv, "value")) {
+		int fd;
+
+		if (!value) {
+			if (value_size)
+				err("duplicate value\n");
+			else
+				err("unnecessary value\n");
+			return -1;
+		}
+
+		argv++;
+
+		if (map_is_map_of_maps(info->type)) {
+			int argc = 2;
+
+			if (value_size != 4) {
+				err("value smaller than 4B for map in map?\n");
+				return -1;
+			}
+			if (!argv[0] || !argv[1]) {
+				err("not enough value arguments for map in map\n");
+				return -1;
+			}
+
+			fd = map_parse_fd(&argc, &argv);
+			if (fd < 0)
+				return -1;
+
+			*value_fd = value;
+			**value_fd = fd;
+		} else if (map_is_map_of_progs(info->type)) {
+			int argc = 2;
+
+			if (value_size != 4) {
+				err("value smaller than 4B for map of progs?\n");
+				return -1;
+			}
+			if (!argv[0] || !argv[1]) {
+				err("not enough value arguments for map of progs\n");
+				return -1;
+			}
+
+			fd = prog_parse_fd(&argc, &argv);
+			if (fd < 0)
+				return -1;
+
+			*value_fd = value;
+			**value_fd = fd;
+		} else {
+			argv = parse_bytes(argv, "value", value, value_size);
+			if (!argv)
+				return -1;
+		}
+
+		return parse_elem(argv, info, key, NULL, key_size, value_size,
+				  flags, NULL);
+	} else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") ||
+		   is_prefix(*argv, "exist")) {
+		if (!flags) {
+			err("flags specified multiple times: %s\n", *argv);
+			return -1;
+		}
+
+		if (is_prefix(*argv, "any"))
+			*flags = BPF_ANY;
+		else if (is_prefix(*argv, "noexist"))
+			*flags = BPF_NOEXIST;
+		else if (is_prefix(*argv, "exist"))
+			*flags = BPF_EXIST;
+
+		return parse_elem(argv + 1, info, key, value, key_size,
+				  value_size, NULL, value_fd);
+	}
+
+	err("expected key or value, got: %s\n", *argv);
+	return -1;
+}
+
+static int show_map_close(int fd, struct bpf_map_info *info)
+{
+	char *memlock;
+
+	memlock = get_fdinfo(fd, "memlock");
+	close(fd);
+
+	printf("%u: ", info->id);
+	if (info->type < ARRAY_SIZE(map_type_name))
+		printf("%s  ", map_type_name[info->type]);
+	else
+		printf("type %u  ", info->type);
+
+	if (*info->name)
+		printf("name %s  ", info->name);
+
+	printf("flags 0x%x\n", info->map_flags);
+	printf("\tkey %uB  value %uB  max_entries %u",
+	       info->key_size, info->value_size, info->max_entries);
+
+	if (memlock)
+		printf("  memlock %sB", memlock);
+	free(memlock);
+
+	printf("\n");
+
+	return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	if (argc == 2) {
+		fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+		if (fd < 0)
+			return -1;
+
+		return show_map_close(fd, &info);
+	}
+
+	if (argc)
+		return BAD_ARG();
+
+	while (true) {
+		err = bpf_map_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT)
+				break;
+			err("can't get next map: %s\n", strerror(errno));
+			if (errno == EINVAL)
+				err("kernel too old?\n");
+			return -1;
+		}
+
+		fd = bpf_map_get_fd_by_id(id);
+		if (fd < 0) {
+			err("can't get map by id (%u): %s\n",
+			    id, strerror(errno));
+			return -1;
+		}
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			err("can't get map info: %s\n", strerror(errno));
+			close(fd);
+			return -1;
+		}
+
+		show_map_close(fd, &info);
+	}
+
+	return errno == ENOENT ? 0 : -1;
+}
+
+static int do_dump(int argc, char **argv)
+{
+	void *key, *value, *prev_key;
+	unsigned int num_elems = 0;
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	int err;
+	int fd;
+
+	if (argc != 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
+		err("Dumping maps of maps and program maps not supported\n");
+		close(fd);
+		return -1;
+	}
+
+	key = malloc(info.key_size);
+	value = alloc_value(&info);
+	if (!key || !value) {
+		err("mem alloc failed\n");
+		err = -1;
+		goto exit_free;
+	}
+
+	prev_key = NULL;
+	while (true) {
+		err = bpf_map_get_next_key(fd, prev_key, key);
+		if (err) {
+			if (errno == ENOENT)
+				err = 0;
+			break;
+		}
+
+		if (!bpf_map_lookup_elem(fd, key, value)) {
+			print_entry(&info, key, value);
+		} else {
+			info("can't lookup element with key: ");
+			print_hex(key, info.key_size, " ");
+			printf("\n");
+		}
+
+		prev_key = key;
+		num_elems++;
+	}
+
+	printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : "");
+
+exit_free:
+	free(key);
+	free(value);
+	close(fd);
+
+	return err;
+}
+
+static int do_update(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	__u32 *value_fd = NULL;
+	__u32 flags = BPF_ANY;
+	void *key, *value;
+	int fd, err;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	value = alloc_value(&info);
+	if (!key || !value) {
+		err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	err = parse_elem(argv, &info, key, value, info.key_size,
+			 info.value_size, &flags, &value_fd);
+	if (err)
+		goto exit_free;
+
+	err = bpf_map_update_elem(fd, key, value, flags);
+	if (err) {
+		err("update failed: %s\n", strerror(errno));
+		goto exit_free;
+	}
+
+exit_free:
+	if (value_fd)
+		close(*value_fd);
+	free(key);
+	free(value);
+	close(fd);
+
+	return err;
+}
+
+static int do_lookup(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	void *key, *value;
+	int err;
+	int fd;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	value = alloc_value(&info);
+	if (!key || !value) {
+		err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+	if (err)
+		goto exit_free;
+
+	err = bpf_map_lookup_elem(fd, key, value);
+	if (!err) {
+		print_entry(&info, key, value);
+	} else if (errno == ENOENT) {
+		printf("key:\n");
+		print_hex(key, info.key_size, " ");
+		printf("\n\nNot found\n");
+	} else {
+		err("lookup failed: %s\n", strerror(errno));
+	}
+
+exit_free:
+	free(key);
+	free(value);
+	close(fd);
+
+	return err;
+}
+
+static int do_getnext(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	void *key, *nextkey;
+	int err;
+	int fd;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	nextkey = malloc(info.key_size);
+	if (!key || !nextkey) {
+		err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	if (argc) {
+		err = parse_elem(argv, &info, key, NULL, info.key_size, 0,
+				 NULL, NULL);
+		if (err)
+			goto exit_free;
+	} else {
+		free(key);
+		key = NULL;
+	}
+
+	err = bpf_map_get_next_key(fd, key, nextkey);
+	if (err) {
+		err("can't get next key: %s\n", strerror(errno));
+		goto exit_free;
+	}
+
+	if (key) {
+		printf("key:\n");
+		print_hex(key, info.key_size, " ");
+		printf("\n");
+	} else {
+		printf("key: None\n");
+	}
+
+	printf("next key:\n");
+	print_hex(nextkey, info.key_size, " ");
+	printf("\n");
+
+exit_free:
+	free(nextkey);
+	free(key);
+	close(fd);
+
+	return err;
+}
+
+static int do_delete(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	void *key;
+	int err;
+	int fd;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	if (!key) {
+		err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+	if (err)
+		goto exit_free;
+
+	err = bpf_map_delete_elem(fd, key);
+	if (err)
+		err("delete failed: %s\n", strerror(errno));
+
+exit_free:
+	free(key);
+	close(fd);
+
+	return err;
+}
+
+static int do_pin(int argc, char **argv)
+{
+	return do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+}
+
+static int do_help(int argc, char **argv)
+{
+	fprintf(stderr,
+		"Usage: %s %s show   [MAP]\n"
+		"       %s %s dump    MAP\n"
+		"       %s %s update  MAP  key BYTES value VALUE [UPDATE_FLAGS]\n"
+		"       %s %s lookup  MAP  key BYTES\n"
+		"       %s %s getnext MAP [key BYTES]\n"
+		"       %s %s delete  MAP  key BYTES\n"
+		"       %s %s pin     MAP  FILE\n"
+		"       %s %s help\n"
+		"\n"
+		"       MAP := { id MAP_ID | pinned FILE }\n"
+		"       " HELP_SPEC_PROGRAM "\n"
+		"       VALUE := { BYTES | MAP | PROG }\n"
+		"       UPDATE_FLAGS := { any | exist | noexist }\n"
+		"",
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2]);
+
+	return 0;
+}
+
+static const struct cmd cmds[] = {
+	{ "show",	do_show },
+	{ "help",	do_help },
+	{ "dump",	do_dump },
+	{ "update",	do_update },
+	{ "lookup",	do_lookup },
+	{ "getnext",	do_getnext },
+	{ "delete",	do_delete },
+	{ "pin",	do_pin },
+	{ 0 }
+};
+
+int do_map(int argc, char **argv)
+{
+	return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
new file mode 100644
index 000000000000..421ba89ce86a
--- /dev/null
+++ b/tools/bpf/bpftool/prog.c
@@ -0,0 +1,456 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+static const char * const prog_type_name[] = {
+	[BPF_PROG_TYPE_UNSPEC]		= "unspec",
+	[BPF_PROG_TYPE_SOCKET_FILTER]	= "socket_filter",
+	[BPF_PROG_TYPE_KPROBE]		= "kprobe",
+	[BPF_PROG_TYPE_SCHED_CLS]	= "sched_cls",
+	[BPF_PROG_TYPE_SCHED_ACT]	= "sched_act",
+	[BPF_PROG_TYPE_TRACEPOINT]	= "tracepoint",
+	[BPF_PROG_TYPE_XDP]		= "xdp",
+	[BPF_PROG_TYPE_PERF_EVENT]	= "perf_event",
+	[BPF_PROG_TYPE_CGROUP_SKB]	= "cgroup_skb",
+	[BPF_PROG_TYPE_CGROUP_SOCK]	= "cgroup_sock",
+	[BPF_PROG_TYPE_LWT_IN]		= "lwt_in",
+	[BPF_PROG_TYPE_LWT_OUT]		= "lwt_out",
+	[BPF_PROG_TYPE_LWT_XMIT]	= "lwt_xmit",
+	[BPF_PROG_TYPE_SOCK_OPS]	= "sock_ops",
+	[BPF_PROG_TYPE_SK_SKB]		= "sk_skb",
+};
+
+static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
+{
+	struct timespec real_time_ts, boot_time_ts;
+	time_t wallclock_secs;
+	struct tm load_tm;
+
+	buf[--size] = '\0';
+
+	if (clock_gettime(CLOCK_REALTIME, &real_time_ts) ||
+	    clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) {
+		perror("Can't read clocks");
+		snprintf(buf, size, "%llu", nsecs / 1000000000);
+		return;
+	}
+
+	wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
+		nsecs / 1000000000;
+
+	if (!localtime_r(&wallclock_secs, &load_tm)) {
+		snprintf(buf, size, "%llu", nsecs / 1000000000);
+		return;
+	}
+
+	strftime(buf, size, "%b %d/%H:%M", &load_tm);
+}
+
+static int prog_fd_by_tag(unsigned char *tag)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	unsigned int id = 0;
+	int err;
+	int fd;
+
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			err("%s\n", strerror(errno));
+			return -1;
+		}
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			err("can't get prog by id (%u): %s\n",
+			    id, strerror(errno));
+			return -1;
+		}
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			err("can't get prog info (%u): %s\n",
+			    id, strerror(errno));
+			close(fd);
+			return -1;
+		}
+
+		if (!memcmp(tag, info.tag, BPF_TAG_SIZE))
+			return fd;
+
+		close(fd);
+	}
+}
+
+int prog_parse_fd(int *argc, char ***argv)
+{
+	int fd;
+
+	if (is_prefix(**argv, "id")) {
+		unsigned int id;
+		char *endptr;
+
+		NEXT_ARGP();
+
+		id = strtoul(**argv, &endptr, 0);
+		if (*endptr) {
+			err("can't parse %s as ID\n", **argv);
+			return -1;
+		}
+		NEXT_ARGP();
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0)
+			err("get by id (%u): %s\n", id, strerror(errno));
+		return fd;
+	} else if (is_prefix(**argv, "tag")) {
+		unsigned char tag[BPF_TAG_SIZE];
+
+		NEXT_ARGP();
+
+		if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
+			   tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
+		    != BPF_TAG_SIZE) {
+			err("can't parse tag\n");
+			return -1;
+		}
+		NEXT_ARGP();
+
+		return prog_fd_by_tag(tag);
+	} else if (is_prefix(**argv, "pinned")) {
+		char *path;
+
+		NEXT_ARGP();
+
+		path = **argv;
+		NEXT_ARGP();
+
+		return open_obj_pinned_any(path, BPF_OBJ_PROG);
+	}
+
+	err("expected 'id', 'tag' or 'pinned', got: '%s'?\n", **argv);
+	return -1;
+}
+
+static void show_prog_maps(int fd, u32 num_maps)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	__u32 map_ids[num_maps];
+	unsigned int i;
+	int err;
+
+	info.nr_map_ids = num_maps;
+	info.map_ids = ptr_to_u64(map_ids);
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err || !info.nr_map_ids)
+		return;
+
+	printf("  map_ids ");
+	for (i = 0; i < info.nr_map_ids; i++)
+		printf("%u%s", map_ids[i],
+		       i == info.nr_map_ids - 1 ? "" : ",");
+}
+
+static int show_prog(int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	char *memlock;
+	int err;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err) {
+		err("can't get prog info: %s\n", strerror(errno));
+		return -1;
+	}
+
+	printf("%u: ", info.id);
+	if (info.type < ARRAY_SIZE(prog_type_name))
+		printf("%s  ", prog_type_name[info.type]);
+	else
+		printf("type %u  ", info.type);
+
+	if (*info.name)
+		printf("name %s  ", info.name);
+
+	printf("tag ");
+	print_hex(info.tag, BPF_TAG_SIZE, ":");
+	printf("\n");
+
+	if (info.load_time) {
+		char buf[32];
+
+		print_boot_time(info.load_time, buf, sizeof(buf));
+
+		/* Piggy back on load_time, since 0 uid is a valid one */
+		printf("\tloaded_at %s  uid %u\n", buf, info.created_by_uid);
+	}
+
+	printf("\txlated %uB", info.xlated_prog_len);
+
+	if (info.jited_prog_len)
+		printf("  jited %uB", info.jited_prog_len);
+	else
+		printf("  not jited");
+
+	memlock = get_fdinfo(fd, "memlock");
+	if (memlock)
+		printf("  memlock %sB", memlock);
+	free(memlock);
+
+	if (info.nr_map_ids)
+		show_prog_maps(fd, info.nr_map_ids);
+
+	printf("\n");
+
+	return 0;
+}
+
+static int do_show(int argc, char **argv)
+{	__u32 id = 0;
+	int err;
+	int fd;
+
+	if (argc == 2) {
+		fd = prog_parse_fd(&argc, &argv);
+		if (fd < 0)
+			return -1;
+
+		return show_prog(fd);
+	}
+
+	if (argc)
+		return BAD_ARG();
+
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT)
+				break;
+			err("can't get next program: %s\n", strerror(errno));
+			if (errno == EINVAL)
+				err("kernel too old?\n");
+			return -1;
+		}
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			err("can't get prog by id (%u): %s\n",
+			    id, strerror(errno));
+			return -1;
+		}
+
+		err = show_prog(fd);
+		close(fd);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int do_dump(int argc, char **argv)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	bool can_disasm = false;
+	unsigned int buf_size;
+	char *filepath = NULL;
+	bool opcodes = false;
+	unsigned char *buf;
+	__u32 *member_len;
+	__u64 *member_ptr;
+	ssize_t n;
+	int err;
+	int fd;
+
+	if (is_prefix(*argv, "jited")) {
+		member_len = &info.jited_prog_len;
+		member_ptr = &info.jited_prog_insns;
+		can_disasm = true;
+	} else if (is_prefix(*argv, "xlated")) {
+		member_len = &info.xlated_prog_len;
+		member_ptr = &info.xlated_prog_insns;
+	} else {
+		err("expected 'xlated' or 'jited', got: %s\n", *argv);
+		return -1;
+	}
+	NEXT_ARG();
+
+	if (argc < 2)
+		usage();
+
+	fd = prog_parse_fd(&argc, &argv);
+	if (fd < 0)
+		return -1;
+
+	if (is_prefix(*argv, "file")) {
+		NEXT_ARG();
+		if (!argc) {
+			err("expected file path\n");
+			return -1;
+		}
+
+		filepath = *argv;
+		NEXT_ARG();
+	} else if (is_prefix(*argv, "opcodes")) {
+		opcodes = true;
+		NEXT_ARG();
+	}
+
+	if (!filepath && !can_disasm) {
+		err("expected 'file' got %s\n", *argv);
+		return -1;
+	}
+	if (argc) {
+		usage();
+		return -1;
+	}
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err) {
+		err("can't get prog info: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (!*member_len) {
+		info("no instructions returned\n");
+		close(fd);
+		return 0;
+	}
+
+	buf_size = *member_len;
+
+	buf = malloc(buf_size);
+	if (!buf) {
+		err("mem alloc failed\n");
+		close(fd);
+		return -1;
+	}
+
+	memset(&info, 0, sizeof(info));
+
+	*member_ptr = ptr_to_u64(buf);
+	*member_len = buf_size;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	close(fd);
+	if (err) {
+		err("can't get prog info: %s\n", strerror(errno));
+		goto err_free;
+	}
+
+	if (*member_len > buf_size) {
+		info("too many instructions returned\n");
+		goto err_free;
+	}
+
+	if (filepath) {
+		fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
+		if (fd < 0) {
+			err("can't open file %s: %s\n", filepath,
+			    strerror(errno));
+			goto err_free;
+		}
+
+		n = write(fd, buf, *member_len);
+		close(fd);
+		if (n != *member_len) {
+			err("error writing output file: %s\n",
+			    n < 0 ? strerror(errno) : "short write");
+			goto err_free;
+		}
+	} else {
+		disasm_print_insn(buf, *member_len, opcodes);
+	}
+
+	free(buf);
+
+	return 0;
+
+err_free:
+	free(buf);
+	return -1;
+}
+
+static int do_pin(int argc, char **argv)
+{
+	return do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+}
+
+static int do_help(int argc, char **argv)
+{
+	fprintf(stderr,
+		"Usage: %s %s show [PROG]\n"
+		"       %s %s dump xlated PROG  file FILE\n"
+		"       %s %s dump jited  PROG [file FILE] [opcodes]\n"
+		"       %s %s pin   PROG FILE\n"
+		"       %s %s help\n"
+		"\n"
+		"       " HELP_SPEC_PROGRAM "\n"
+		"",
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2]);
+
+	return 0;
+}
+
+static const struct cmd cmds[] = {
+	{ "show",	do_show },
+	{ "dump",	do_dump },
+	{ "pin",	do_pin },
+	{ 0 }
+};
+
+int do_prog(int argc, char **argv)
+{
+	return cmd_select(cmds, argc, argv, do_help);
+}
-- 
cgit v1.2.3


From ff69c21a85a4ed3d8dcf79dd750a0a9eda4fca83 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 4 Oct 2017 20:10:05 -0700
Subject: tools: bpftool: add documentation

Add documentation for bpftool.  Separate files for each subcommand.
Use rst format.  Documentation is compiled into man pages using
rst2man.

Signed-off-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/Makefile         |  34 +++++++
 tools/bpf/bpftool/Documentation/bpftool-map.rst  | 110 +++++++++++++++++++++++
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  79 ++++++++++++++++
 tools/bpf/bpftool/Documentation/bpftool.rst      |  34 +++++++
 tools/bpf/bpftool/Makefile                       |   6 ++
 5 files changed, 263 insertions(+)
 create mode 100644 tools/bpf/bpftool/Documentation/Makefile
 create mode 100644 tools/bpf/bpftool/Documentation/bpftool-map.rst
 create mode 100644 tools/bpf/bpftool/Documentation/bpftool-prog.rst
 create mode 100644 tools/bpf/bpftool/Documentation/bpftool.rst

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
new file mode 100644
index 000000000000..bde77d7c4390
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -0,0 +1,34 @@
+include ../../../scripts/Makefile.include
+include ../../../scripts/utilities.mak
+
+INSTALL ?= install
+RM ?= rm -f
+
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
+prefix?=$(HOME)
+endif
+mandir ?= $(prefix)/share/man
+man8dir = $(mandir)/man8
+
+MAN8_RST = $(wildcard *.rst)
+
+_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
+DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
+
+man: man8
+man8: $(DOC_MAN8)
+
+$(OUTPUT)%.8: %.rst
+	rst2man $< > $@
+
+clean:
+	$(call QUIET_CLEAN, Documentation) $(RM) $(DOC_MAN8)
+
+install: man
+	$(call QUIET_INSTALL, Documentation-man) \
+		$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir); \
+		$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir);
+
+.PHONY: man man8 clean install
+.DEFAULT_GOAL := man
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
new file mode 100644
index 000000000000..ff63e89e4b6c
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -0,0 +1,110 @@
+================
+bpftool-map
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF maps
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** **map** *COMMAND*
+
+	*COMMANDS* :=
+	{ show | dump | update | lookup | getnext | delete | pin | help }
+
+MAP COMMANDS
+=============
+
+|	**bpftool** map show   [*MAP*]
+|	**bpftool** map dump    *MAP*
+|	**bpftool** map update  *MAP*  key *BYTES*   value *VALUE* [*UPDATE_FLAGS*]
+|	**bpftool** map lookup  *MAP*  key *BYTES*
+|	**bpftool** map getnext *MAP* [key *BYTES*]
+|	**bpftool** map delete  *MAP*  key *BYTES*
+|	**bpftool** map pin     *MAP*  *FILE*
+|	**bpftool** map help
+|
+|	*MAP* := { id MAP_ID | pinned FILE }
+|	*VALUE* := { BYTES | MAP | PROGRAM }
+|	*UPDATE_FLAGS* := { any | exist | noexist }
+
+DESCRIPTION
+===========
+	**bpftool map show**   [*MAP*]
+		  Show information about loaded maps.  If *MAP* is specified
+		  show information only about given map, otherwise list all
+		  maps currently loaded on the system.
+
+		  Output will start with map ID followed by map type and
+		  zero or more named attributes (depending on kernel version).
+
+	**bpftool map dump**    *MAP*
+		  Dump all entries in a given *MAP*.
+
+	**bpftool map update**  *MAP*  **key** *BYTES*   **value** *VALUE* [*UPDATE_FLAGS*]
+		  Update map entry for a given *KEY*.
+
+		  *UPDATE_FLAGS* can be one of: **any** update existing entry
+		  or add if doesn't exit; **exist** update only if entry already
+		  exists; **noexist** update only if entry doesn't exist.
+
+	**bpftool map lookup**  *MAP*  **key** *BYTES*
+		  Lookup **key** in the map.
+
+	**bpftool map getnext** *MAP* [**key** *BYTES*]
+		  Get next key.  If *key* is not specified, get first key.
+
+	**bpftool map delete**  *MAP*  **key** *BYTES*
+		  Remove entry from the map.
+
+	**bpftool map pin**     *MAP*  *FILE*
+		  Pin map *MAP* as *FILE*.
+
+		  Note: *FILE* must be located in *bpffs* mount.
+
+	**bpftool map help**
+		  Print short help message.
+
+EXAMPLES
+========
+**# bpftool map show**
+::
+
+  10: hash  name some_map  flags 0x0
+	key 4B  value 8B  max_entries 2048  memlock 167936B
+
+**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04**
+
+**# bpftool map lookup id 10 key 0 1 2 3**
+
+::
+
+  key: 00 01 02 03 value: 00 01 02 03 04 05 06 07
+
+
+**# bpftool map dump id 10**
+::
+
+  key: 00 01 02 03  value: 00 01 02 03 04 05 06 07
+  key: 0d 00 07 00  value: 02 00 00 00 01 02 03 04
+  Found 2 elements
+
+**# bpftool map getnext id 10 key 0 1 2 3**
+::
+
+  key:
+  00 01 02 03
+  next key:
+  0d 00 07 00
+
+|
+| **# mount -t bpf none /sys/fs/bpf/**
+| **# bpftool map pin id 10 /sys/fs/bpf/map**
+| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00**
+
+SEE ALSO
+========
+	**bpftool**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
new file mode 100644
index 000000000000..57fc4b9924ea
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -0,0 +1,79 @@
+================
+bpftool-prog
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF progs
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+|	**bpftool** prog show [*PROG*]
+|	**bpftool** prog dump xlated *PROG*  file *FILE*
+|	**bpftool** prog dump jited  *PROG* [file *FILE*] [opcodes]
+|	**bpftool** prog pin *PROG* *FILE*
+|	**bpftool** prog help
+|
+|	*PROG* := { id *PROG_ID* | pinned *FILE* | tag *PROG_TAG* }
+
+DESCRIPTION
+===========
+	**bpftool prog show** [*PROG*]
+		  Show information about loaded programs.  If *PROG* is
+		  specified show information only about given program, otherwise
+		  list all programs currently loaded on the system.
+
+		  Output will start with program ID followed by program type and
+		  zero or more named attributes (depending on kernel version).
+
+	**bpftool prog dump xlated** *PROG*  **file** *FILE*
+		  Dump eBPF instructions of the program from the kernel to a
+		  file.
+
+	**bpftool prog dump jited**  *PROG* [**file** *FILE*] [**opcodes**]
+		  Dump jited image (host machine code) of the program.
+		  If *FILE* is specified image will be written to a file,
+		  otherwise it will be disassembled and printed to stdout.
+
+		  **opcodes** controls if raw opcodes will be printed.
+
+	**bpftool prog pin** *PROG* *FILE*
+		  Pin program *PROG* as *FILE*.
+
+		  Note: *FILE* must be located in *bpffs* mount.
+
+	**bpftool prog help**
+		  Print short help message.
+
+EXAMPLES
+========
+**# bpftool prog show**
+::
+
+  10: xdp  name some_prog  tag 00:5a:3d:21:23:62:0c:8b
+	loaded_at Sep 29/20:11  uid 0
+	xlated 528B  jited 370B  memlock 4096B  map_ids 10
+
+|
+| **# bpftool prog dump xlated id 10 file /tmp/t**
+| **# ls -l /tmp/t**
+|   -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
+
+|
+| **# bpftool prog dum jited pinned /sys/fs/bpf/prog**
+
+::
+
+    push   %rbp
+    mov    %rsp,%rbp
+    sub    $0x228,%rsp
+    sub    $0x28,%rbp
+    mov    %rbx,0x0(%rbp)
+
+
+
+SEE ALSO
+========
+	**bpftool**\ (8), **bpftool-map**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
new file mode 100644
index 000000000000..f1df1893fb54
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -0,0 +1,34 @@
+================
+BPFTOOL
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF programs and maps
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** *OBJECT* { *COMMAND* | help }
+
+	**bpftool** batch file *FILE*
+
+	*OBJECT* := { **map** | **program** }
+
+	*MAP-COMMANDS* :=
+	{ show | dump | update | lookup | getnext | delete | pin | help }
+
+	*PROG-COMMANDS* := { show | dump jited | dump xlated | pin | help }
+
+DESCRIPTION
+===========
+	*bpftool* allows for inspection and simple modification of BPF objects
+	on the system.
+
+	Note that format of the output of all tools is not guaranteed to be
+	stable and should not be depended upon.
+
+SEE ALSO
+========
+	**bpftool-map**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index a7151f47fb40..8705ee44664d 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -74,6 +74,12 @@ clean: $(LIBBPF)-clean
 install:
 	install $(OUTPUT)bpftool $(prefix)/sbin/bpftool
 
+doc:
+	$(Q)$(MAKE) -C Documentation/
+
+doc-install:
+	$(Q)$(MAKE) -C Documentation/ install
+
 FORCE:
 
 .PHONY: all clean FORCE
-- 
cgit v1.2.3


From 0b02503384301e4c2db13f1045a1ddbaca2ba0ce Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 5 Oct 2017 16:46:54 -0400
Subject: VSOCK: add tools/testing/vsock/vsock_diag_test

This patch adds tests for the vsock_diag.ko module.

These tests are not self-tests because they require manual set up of a
KVM or VMware guest.  Please see tools/testing/vsock/README for
instructions.

The control.h and timeout.h infrastructure can be used for additional
AF_VSOCK tests in the future.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                           |   1 +
 tools/testing/vsock/.gitignore        |   2 +
 tools/testing/vsock/Makefile          |   9 +
 tools/testing/vsock/README            |  36 ++
 tools/testing/vsock/control.c         | 219 +++++++++++
 tools/testing/vsock/control.h         |  13 +
 tools/testing/vsock/timeout.c         |  64 ++++
 tools/testing/vsock/timeout.h         |  14 +
 tools/testing/vsock/vsock_diag_test.c | 681 ++++++++++++++++++++++++++++++++++
 9 files changed, 1039 insertions(+)
 create mode 100644 tools/testing/vsock/.gitignore
 create mode 100644 tools/testing/vsock/Makefile
 create mode 100644 tools/testing/vsock/README
 create mode 100644 tools/testing/vsock/control.c
 create mode 100644 tools/testing/vsock/control.h
 create mode 100644 tools/testing/vsock/timeout.c
 create mode 100644 tools/testing/vsock/timeout.h
 create mode 100644 tools/testing/vsock/vsock_diag_test.c

(limited to 'tools')

diff --git a/MAINTAINERS b/MAINTAINERS
index 0fd9121953bb..f0c37be4e04a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14294,6 +14294,7 @@ F:	net/vmw_vsock/virtio_transport.c
 F:	drivers/net/vsockmon.c
 F:	drivers/vhost/vsock.c
 F:	drivers/vhost/vsock.h
+F:	tools/testing/vsock/
 
 VIRTIO CONSOLE DRIVER
 M:	Amit Shah <amit@kernel.org>
diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore
new file mode 100644
index 000000000000..dc5f11faf530
--- /dev/null
+++ b/tools/testing/vsock/.gitignore
@@ -0,0 +1,2 @@
+*.d
+vsock_diag_test
diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
new file mode 100644
index 000000000000..66ba0924194d
--- /dev/null
+++ b/tools/testing/vsock/Makefile
@@ -0,0 +1,9 @@
+all: test
+test: vsock_diag_test
+vsock_diag_test: vsock_diag_test.o timeout.o control.o
+
+CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE
+.PHONY: all test clean
+clean:
+	${RM} *.o *.d vsock_diag_test
+-include *.d
diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README
new file mode 100644
index 000000000000..2cc6d7302db6
--- /dev/null
+++ b/tools/testing/vsock/README
@@ -0,0 +1,36 @@
+AF_VSOCK test suite
+-------------------
+These tests exercise net/vmw_vsock/ host<->guest sockets for VMware, KVM, and
+Hyper-V.
+
+The following tests are available:
+
+  * vsock_diag_test - vsock_diag.ko module for listing open sockets
+
+The following prerequisite steps are not automated and must be performed prior
+to running tests:
+
+1. Build the kernel and these tests.
+2. Install the kernel and tests on the host.
+3. Install the kernel and tests inside the guest.
+4. Boot the guest and ensure that the AF_VSOCK transport is enabled.
+
+Invoke test binaries in both directions as follows:
+
+  # host=server, guest=client
+  (host)# $TEST_BINARY --mode=server \
+                       --control-port=1234 \
+                       --peer-cid=3
+  (guest)# $TEST_BINARY --mode=client \
+                        --control-host=$HOST_IP \
+                        --control-port=1234 \
+                        --peer-cid=2
+
+  # host=client, guest=server
+  (guest)# $TEST_BINARY --mode=server \
+                        --control-port=1234 \
+                        --peer-cid=2
+  (host)# $TEST_BINARY --mode=client \
+                       --control-port=$GUEST_IP \
+                       --control-port=1234 \
+                       --peer-cid=3
diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c
new file mode 100644
index 000000000000..90fd47f0e422
--- /dev/null
+++ b/tools/testing/vsock/control.c
@@ -0,0 +1,219 @@
+/* Control socket for client/server test execution
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/* The client and server may need to coordinate to avoid race conditions like
+ * the client attempting to connect to a socket that the server is not
+ * listening on yet.  The control socket offers a communications channel for
+ * such coordination tasks.
+ *
+ * If the client calls control_expectln("LISTENING"), then it will block until
+ * the server calls control_writeln("LISTENING").  This provides a simple
+ * mechanism for coordinating between the client and the server.
+ */
+
+#include <errno.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "timeout.h"
+#include "control.h"
+
+static int control_fd = -1;
+
+/* Open the control socket, either in server or client mode */
+void control_init(const char *control_host,
+		  const char *control_port,
+		  bool server)
+{
+	struct addrinfo hints = {
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *result = NULL;
+	struct addrinfo *ai;
+	int ret;
+
+	ret = getaddrinfo(control_host, control_port, &hints, &result);
+	if (ret != 0) {
+		fprintf(stderr, "%s\n", gai_strerror(ret));
+		exit(EXIT_FAILURE);
+	}
+
+	for (ai = result; ai; ai = ai->ai_next) {
+		int fd;
+		int val = 1;
+
+		fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+		if (fd < 0)
+			continue;
+
+		if (!server) {
+			if (connect(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+				goto next;
+			control_fd = fd;
+			printf("Control socket connected to %s:%s.\n",
+			       control_host, control_port);
+			break;
+		}
+
+		if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
+			       &val, sizeof(val)) < 0) {
+			perror("setsockopt");
+			exit(EXIT_FAILURE);
+		}
+
+		if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+			goto next;
+		if (listen(fd, 1) < 0)
+			goto next;
+
+		printf("Control socket listening on %s:%s\n",
+		       control_host, control_port);
+		fflush(stdout);
+
+		control_fd = accept(fd, NULL, 0);
+		close(fd);
+
+		if (control_fd < 0) {
+			perror("accept");
+			exit(EXIT_FAILURE);
+		}
+		printf("Control socket connection accepted...\n");
+		break;
+
+next:
+		close(fd);
+	}
+
+	if (control_fd < 0) {
+		fprintf(stderr, "Control socket initialization failed.  Invalid address %s:%s?\n",
+			control_host, control_port);
+		exit(EXIT_FAILURE);
+	}
+
+	freeaddrinfo(result);
+}
+
+/* Free resources */
+void control_cleanup(void)
+{
+	close(control_fd);
+	control_fd = -1;
+}
+
+/* Write a line to the control socket */
+void control_writeln(const char *str)
+{
+	ssize_t len = strlen(str);
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+
+	do {
+		ret = send(control_fd, str, len, MSG_MORE);
+		timeout_check("send");
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret != len) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	do {
+		ret = send(control_fd, "\n", 1, 0);
+		timeout_check("send");
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret != 1) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	timeout_end();
+}
+
+/* Return the next line from the control socket (without the trailing newline).
+ *
+ * The program terminates if a timeout occurs.
+ *
+ * The caller must free() the returned string.
+ */
+char *control_readln(void)
+{
+	char *buf = NULL;
+	size_t idx = 0;
+	size_t buflen = 0;
+
+	timeout_begin(TIMEOUT);
+
+	for (;;) {
+		ssize_t ret;
+
+		if (idx >= buflen) {
+			char *new_buf;
+
+			new_buf = realloc(buf, buflen + 80);
+			if (!new_buf) {
+				perror("realloc");
+				exit(EXIT_FAILURE);
+			}
+
+			buf = new_buf;
+			buflen += 80;
+		}
+
+		do {
+			ret = recv(control_fd, &buf[idx], 1, 0);
+			timeout_check("recv");
+		} while (ret < 0 && errno == EINTR);
+
+		if (ret == 0) {
+			fprintf(stderr, "unexpected EOF on control socket\n");
+			exit(EXIT_FAILURE);
+		}
+
+		if (ret != 1) {
+			perror("recv");
+			exit(EXIT_FAILURE);
+		}
+
+		if (buf[idx] == '\n') {
+			buf[idx] = '\0';
+			break;
+		}
+
+		idx++;
+	}
+
+	timeout_end();
+
+	return buf;
+}
+
+/* Wait until a given line is received or a timeout occurs */
+void control_expectln(const char *str)
+{
+	char *line;
+
+	line = control_readln();
+	if (strcmp(str, line) != 0) {
+		fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n",
+			str, line);
+		exit(EXIT_FAILURE);
+	}
+
+	free(line);
+}
diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h
new file mode 100644
index 000000000000..54a07efd267c
--- /dev/null
+++ b/tools/testing/vsock/control.h
@@ -0,0 +1,13 @@
+#ifndef CONTROL_H
+#define CONTROL_H
+
+#include <stdbool.h>
+
+void control_init(const char *control_host, const char *control_port,
+		  bool server);
+void control_cleanup(void);
+void control_writeln(const char *str);
+char *control_readln(void);
+void control_expectln(const char *str);
+
+#endif /* CONTROL_H */
diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c
new file mode 100644
index 000000000000..c49b3003b2db
--- /dev/null
+++ b/tools/testing/vsock/timeout.c
@@ -0,0 +1,64 @@
+/* Timeout API for single-threaded programs that use blocking
+ * syscalls (read/write/send/recv/connect/accept).
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/* Use the following pattern:
+ *
+ *   timeout_begin(TIMEOUT);
+ *   do {
+ *       ret = accept(...);
+ *       timeout_check("accept");
+ *   } while (ret < 0 && ret == EINTR);
+ *   timeout_end();
+ */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <stdio.h>
+#include "timeout.h"
+
+static volatile bool timeout;
+
+/* SIGALRM handler function.  Do not use sleep(2), alarm(2), or
+ * setitimer(2) while using this API - they may interfere with each
+ * other.
+ */
+void sigalrm(int signo)
+{
+	timeout = true;
+}
+
+/* Start a timeout.  Call timeout_check() to verify that the timeout hasn't
+ * expired.  timeout_end() must be called to stop the timeout.  Timeouts cannot
+ * be nested.
+ */
+void timeout_begin(unsigned int seconds)
+{
+	alarm(seconds);
+}
+
+/* Exit with an error message if the timeout has expired */
+void timeout_check(const char *operation)
+{
+	if (timeout) {
+		fprintf(stderr, "%s timed out\n", operation);
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Stop a timeout */
+void timeout_end(void)
+{
+	alarm(0);
+	timeout = false;
+}
diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h
new file mode 100644
index 000000000000..77db9ce9860a
--- /dev/null
+++ b/tools/testing/vsock/timeout.h
@@ -0,0 +1,14 @@
+#ifndef TIMEOUT_H
+#define TIMEOUT_H
+
+enum {
+	/* Default timeout */
+	TIMEOUT = 10 /* seconds */
+};
+
+void sigalrm(int signo);
+void timeout_begin(unsigned int seconds);
+void timeout_check(const char *operation);
+void timeout_end(void);
+
+#endif /* TIMEOUT_H */
diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c
new file mode 100644
index 000000000000..e896a4af52f4
--- /dev/null
+++ b/tools/testing/vsock/vsock_diag_test.c
@@ -0,0 +1,681 @@
+/*
+ * vsock_diag_test - vsock_diag.ko test suite
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <linux/list.h>
+#include <linux/net.h>
+#include <linux/netlink.h>
+#include <linux/sock_diag.h>
+#include <netinet/tcp.h>
+
+#include "../../../include/uapi/linux/vm_sockets.h"
+#include "../../../include/uapi/linux/vm_sockets_diag.h"
+
+#include "timeout.h"
+#include "control.h"
+
+enum test_mode {
+	TEST_MODE_UNSET,
+	TEST_MODE_CLIENT,
+	TEST_MODE_SERVER
+};
+
+/* Per-socket status */
+struct vsock_stat {
+	struct list_head list;
+	struct vsock_diag_msg msg;
+};
+
+static const char *sock_type_str(int type)
+{
+	switch (type) {
+	case SOCK_DGRAM:
+		return "DGRAM";
+	case SOCK_STREAM:
+		return "STREAM";
+	default:
+		return "INVALID TYPE";
+	}
+}
+
+static const char *sock_state_str(int state)
+{
+	switch (state) {
+	case TCP_CLOSE:
+		return "UNCONNECTED";
+	case TCP_SYN_SENT:
+		return "CONNECTING";
+	case TCP_ESTABLISHED:
+		return "CONNECTED";
+	case TCP_CLOSING:
+		return "DISCONNECTING";
+	case TCP_LISTEN:
+		return "LISTEN";
+	default:
+		return "INVALID STATE";
+	}
+}
+
+static const char *sock_shutdown_str(int shutdown)
+{
+	switch (shutdown) {
+	case 1:
+		return "RCV_SHUTDOWN";
+	case 2:
+		return "SEND_SHUTDOWN";
+	case 3:
+		return "RCV_SHUTDOWN | SEND_SHUTDOWN";
+	default:
+		return "0";
+	}
+}
+
+static void print_vsock_addr(FILE *fp, unsigned int cid, unsigned int port)
+{
+	if (cid == VMADDR_CID_ANY)
+		fprintf(fp, "*:");
+	else
+		fprintf(fp, "%u:", cid);
+
+	if (port == VMADDR_PORT_ANY)
+		fprintf(fp, "*");
+	else
+		fprintf(fp, "%u", port);
+}
+
+static void print_vsock_stat(FILE *fp, struct vsock_stat *st)
+{
+	print_vsock_addr(fp, st->msg.vdiag_src_cid, st->msg.vdiag_src_port);
+	fprintf(fp, " ");
+	print_vsock_addr(fp, st->msg.vdiag_dst_cid, st->msg.vdiag_dst_port);
+	fprintf(fp, " %s %s %s %u\n",
+		sock_type_str(st->msg.vdiag_type),
+		sock_state_str(st->msg.vdiag_state),
+		sock_shutdown_str(st->msg.vdiag_shutdown),
+		st->msg.vdiag_ino);
+}
+
+static void print_vsock_stats(FILE *fp, struct list_head *head)
+{
+	struct vsock_stat *st;
+
+	list_for_each_entry(st, head, list)
+		print_vsock_stat(fp, st);
+}
+
+static struct vsock_stat *find_vsock_stat(struct list_head *head, int fd)
+{
+	struct vsock_stat *st;
+	struct stat stat;
+
+	if (fstat(fd, &stat) < 0) {
+		perror("fstat");
+		exit(EXIT_FAILURE);
+	}
+
+	list_for_each_entry(st, head, list)
+		if (st->msg.vdiag_ino == stat.st_ino)
+			return st;
+
+	fprintf(stderr, "cannot find fd %d\n", fd);
+	exit(EXIT_FAILURE);
+}
+
+static void check_no_sockets(struct list_head *head)
+{
+	if (!list_empty(head)) {
+		fprintf(stderr, "expected no sockets\n");
+		print_vsock_stats(stderr, head);
+		exit(1);
+	}
+}
+
+static void check_num_sockets(struct list_head *head, int expected)
+{
+	struct list_head *node;
+	int n = 0;
+
+	list_for_each(node, head)
+		n++;
+
+	if (n != expected) {
+		fprintf(stderr, "expected %d sockets, found %d\n",
+			expected, n);
+		print_vsock_stats(stderr, head);
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void check_socket_state(struct vsock_stat *st, __u8 state)
+{
+	if (st->msg.vdiag_state != state) {
+		fprintf(stderr, "expected socket state %#x, got %#x\n",
+			state, st->msg.vdiag_state);
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void send_req(int fd)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK,
+	};
+	struct {
+		struct nlmsghdr nlh;
+		struct vsock_diag_req vreq;
+	} req = {
+		.nlh = {
+			.nlmsg_len = sizeof(req),
+			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
+			.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP,
+		},
+		.vreq = {
+			.sdiag_family = AF_VSOCK,
+			.vdiag_states = ~(__u32)0,
+		},
+	};
+	struct iovec iov = {
+		.iov_base = &req,
+		.iov_len = sizeof(req),
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+
+	for (;;) {
+		if (sendmsg(fd, &msg, 0) < 0) {
+			if (errno == EINTR)
+				continue;
+
+			perror("sendmsg");
+			exit(EXIT_FAILURE);
+		}
+
+		return;
+	}
+}
+
+static ssize_t recv_resp(int fd, void *buf, size_t len)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK,
+	};
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = len,
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	ssize_t ret;
+
+	do {
+		ret = recvmsg(fd, &msg, 0);
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret < 0) {
+		perror("recvmsg");
+		exit(EXIT_FAILURE);
+	}
+
+	return ret;
+}
+
+static void add_vsock_stat(struct list_head *sockets,
+			   const struct vsock_diag_msg *resp)
+{
+	struct vsock_stat *st;
+
+	st = malloc(sizeof(*st));
+	if (!st) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	st->msg = *resp;
+	list_add_tail(&st->list, sockets);
+}
+
+/*
+ * Read vsock stats into a list.
+ */
+static void read_vsock_stat(struct list_head *sockets)
+{
+	long buf[8192 / sizeof(long)];
+	int fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	send_req(fd);
+
+	for (;;) {
+		const struct nlmsghdr *h;
+		ssize_t ret;
+
+		ret = recv_resp(fd, buf, sizeof(buf));
+		if (ret == 0)
+			goto done;
+		if (ret < sizeof(*h)) {
+			fprintf(stderr, "short read of %zd bytes\n", ret);
+			exit(EXIT_FAILURE);
+		}
+
+		h = (struct nlmsghdr *)buf;
+
+		while (NLMSG_OK(h, ret)) {
+			if (h->nlmsg_type == NLMSG_DONE)
+				goto done;
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				const struct nlmsgerr *err = NLMSG_DATA(h);
+
+				if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
+					fprintf(stderr, "NLMSG_ERROR\n");
+				else {
+					errno = -err->error;
+					perror("NLMSG_ERROR");
+				}
+
+				exit(EXIT_FAILURE);
+			}
+
+			if (h->nlmsg_type != SOCK_DIAG_BY_FAMILY) {
+				fprintf(stderr, "unexpected nlmsg_type %#x\n",
+					h->nlmsg_type);
+				exit(EXIT_FAILURE);
+			}
+			if (h->nlmsg_len <
+			    NLMSG_LENGTH(sizeof(struct vsock_diag_msg))) {
+				fprintf(stderr, "short vsock_diag_msg\n");
+				exit(EXIT_FAILURE);
+			}
+
+			add_vsock_stat(sockets, NLMSG_DATA(h));
+
+			h = NLMSG_NEXT(h, ret);
+		}
+	}
+
+done:
+	close(fd);
+}
+
+static void free_sock_stat(struct list_head *sockets)
+{
+	struct vsock_stat *st;
+	struct vsock_stat *next;
+
+	list_for_each_entry_safe(st, next, sockets, list)
+		free(st);
+}
+
+static void test_no_sockets(unsigned int peer_cid)
+{
+	LIST_HEAD(sockets);
+
+	read_vsock_stat(&sockets);
+
+	check_no_sockets(&sockets);
+
+	free_sock_stat(&sockets);
+}
+
+static void test_listen_socket_server(unsigned int peer_cid)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = 1234,
+			.svm_cid = VMADDR_CID_ANY,
+		},
+	};
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+	int fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, fd);
+	check_socket_state(st, TCP_LISTEN);
+
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static void test_connect_client(unsigned int peer_cid)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = 1234,
+			.svm_cid = peer_cid,
+		},
+	};
+	int fd;
+	int ret;
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+
+	control_expectln("LISTENING");
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = connect(fd, &addr.sa, sizeof(addr.svm));
+		timeout_check("connect");
+	} while (ret < 0 && errno == EINTR);
+	timeout_end();
+
+	if (ret < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, fd);
+	check_socket_state(st, TCP_ESTABLISHED);
+
+	control_expectln("DONE");
+	control_writeln("DONE");
+
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static void test_connect_server(unsigned int peer_cid)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = 1234,
+			.svm_cid = VMADDR_CID_ANY,
+		},
+	};
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} clientaddr;
+	socklen_t clientaddr_len = sizeof(clientaddr.svm);
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+	int fd;
+	int client_fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("LISTENING");
+
+	timeout_begin(TIMEOUT);
+	do {
+		client_fd = accept(fd, &clientaddr.sa, &clientaddr_len);
+		timeout_check("accept");
+	} while (client_fd < 0 && errno == EINTR);
+	timeout_end();
+
+	if (client_fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+	if (clientaddr.sa.sa_family != AF_VSOCK) {
+		fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n",
+			clientaddr.sa.sa_family);
+		exit(EXIT_FAILURE);
+	}
+	if (clientaddr.svm.svm_cid != peer_cid) {
+		fprintf(stderr, "expected peer CID %u from accept(2), got %u\n",
+			peer_cid, clientaddr.svm.svm_cid);
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 2);
+	find_vsock_stat(&sockets, fd);
+	st = find_vsock_stat(&sockets, client_fd);
+	check_socket_state(st, TCP_ESTABLISHED);
+
+	control_writeln("DONE");
+	control_expectln("DONE");
+
+	close(client_fd);
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static struct {
+	const char *name;
+	void (*run_client)(unsigned int peer_cid);
+	void (*run_server)(unsigned int peer_cid);
+} test_cases[] = {
+	{
+		.name = "No sockets",
+		.run_server = test_no_sockets,
+	},
+	{
+		.name = "Listen socket",
+		.run_server = test_listen_socket_server,
+	},
+	{
+		.name = "Connect",
+		.run_client = test_connect_client,
+		.run_server = test_connect_server,
+	},
+	{},
+};
+
+static void init_signals(void)
+{
+	struct sigaction act = {
+		.sa_handler = sigalrm,
+	};
+
+	sigaction(SIGALRM, &act, NULL);
+	signal(SIGPIPE, SIG_IGN);
+}
+
+static unsigned int parse_cid(const char *str)
+{
+	char *endptr = NULL;
+	unsigned long int n;
+
+	errno = 0;
+	n = strtoul(str, &endptr, 10);
+	if (errno || *endptr != '\0') {
+		fprintf(stderr, "malformed CID \"%s\"\n", str);
+		exit(EXIT_FAILURE);
+	}
+	return n;
+}
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "control-host",
+		.has_arg = required_argument,
+		.val = 'H',
+	},
+	{
+		.name = "control-port",
+		.has_arg = required_argument,
+		.val = 'P',
+	},
+	{
+		.name = "mode",
+		.has_arg = required_argument,
+		.val = 'm',
+	},
+	{
+		.name = "peer-cid",
+		.has_arg = required_argument,
+		.val = 'p',
+	},
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = '?',
+	},
+	{},
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n"
+		"\n"
+		"  Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n"
+		"  Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n"
+		"\n"
+		"Run vsock_diag.ko tests.  Must be launched in both\n"
+		"guest and host.  One side must use --mode=client and\n"
+		"the other side must use --mode=server.\n"
+		"\n"
+		"A TCP control socket connection is used to coordinate tests\n"
+		"between the client and the server.  The server requires a\n"
+		"listen address and the client requires an address to\n"
+		"connect to.\n"
+		"\n"
+		"The CID of the other side must be given with --peer-cid=<cid>.\n");
+	exit(EXIT_FAILURE);
+}
+
+int main(int argc, char **argv)
+{
+	const char *control_host = NULL;
+	const char *control_port = NULL;
+	int mode = TEST_MODE_UNSET;
+	unsigned int peer_cid = VMADDR_CID_ANY;
+	int i;
+
+	init_signals();
+
+	for (;;) {
+		int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'H':
+			control_host = optarg;
+			break;
+		case 'm':
+			if (strcmp(optarg, "client") == 0)
+				mode = TEST_MODE_CLIENT;
+			else if (strcmp(optarg, "server") == 0)
+				mode = TEST_MODE_SERVER;
+			else {
+				fprintf(stderr, "--mode must be \"client\" or \"server\"\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'p':
+			peer_cid = parse_cid(optarg);
+			break;
+		case 'P':
+			control_port = optarg;
+			break;
+		case '?':
+		default:
+			usage();
+		}
+	}
+
+	if (!control_port)
+		usage();
+	if (mode == TEST_MODE_UNSET)
+		usage();
+	if (peer_cid == VMADDR_CID_ANY)
+		usage();
+
+	if (!control_host) {
+		if (mode != TEST_MODE_SERVER)
+			usage();
+		control_host = "0.0.0.0";
+	}
+
+	control_init(control_host, control_port, mode == TEST_MODE_SERVER);
+
+	for (i = 0; test_cases[i].name; i++) {
+		void (*run)(unsigned int peer_cid);
+
+		printf("%s...", test_cases[i].name);
+		fflush(stdout);
+
+		if (mode == TEST_MODE_CLIENT)
+			run = test_cases[i].run_client;
+		else
+			run = test_cases[i].run_server;
+
+		if (run)
+			run(peer_cid);
+
+		printf("ok\n");
+	}
+
+	control_cleanup();
+	return EXIT_SUCCESS;
+}
-- 
cgit v1.2.3


From b13c5c14dbfd5923d773de9661404ed9600c53ef Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Thu, 5 Oct 2017 10:41:57 -0400
Subject: libbpf: parse maps sections of varying size

This library previously assumed a fixed-size map options structure.
Any new options were ignored.  In order to allow the options structure
to grow and to support parsing older programs, this patch updates
the maps section parsing to handle varying sizes.

Object files with maps sections smaller than expected will have the new
fields initialized to zero.  Object files which have larger than expected
maps sections will be rejected unless all of the unrecognized data is zero.

This change still assumes that each map definition in the maps section
is the same size.

Signed-off-by: Craig Gallek <kraig@google.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/lib/bpf/libbpf.c | 70 +++++++++++++++++++++++++++++---------------------
 1 file changed, 41 insertions(+), 29 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4f402dcdf372..23152890ec60 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -579,31 +579,6 @@ bpf_object__init_kversion(struct bpf_object *obj,
 	return 0;
 }
 
-static int
-bpf_object__validate_maps(struct bpf_object *obj)
-{
-	int i;
-
-	/*
-	 * If there's only 1 map, the only error case should have been
-	 * catched in bpf_object__init_maps().
-	 */
-	if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1))
-		return 0;
-
-	for (i = 1; i < obj->nr_maps; i++) {
-		const struct bpf_map *a = &obj->maps[i - 1];
-		const struct bpf_map *b = &obj->maps[i];
-
-		if (b->offset - a->offset < sizeof(struct bpf_map_def)) {
-			pr_warning("corrupted map section in %s: map \"%s\" too small\n",
-				   obj->path, a->name);
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
 static int compare_bpf_map(const void *_a, const void *_b)
 {
 	const struct bpf_map *a = _a;
@@ -615,7 +590,7 @@ static int compare_bpf_map(const void *_a, const void *_b)
 static int
 bpf_object__init_maps(struct bpf_object *obj)
 {
-	int i, map_idx, nr_maps = 0;
+	int i, map_idx, map_def_sz, nr_maps = 0;
 	Elf_Scn *scn;
 	Elf_Data *data;
 	Elf_Data *symbols = obj->efile.symbols;
@@ -658,6 +633,15 @@ bpf_object__init_maps(struct bpf_object *obj)
 	if (!nr_maps)
 		return 0;
 
+	/* Assume equally sized map definitions */
+	map_def_sz = data->d_size / nr_maps;
+	if (!data->d_size || (data->d_size % nr_maps) != 0) {
+		pr_warning("unable to determine map definition size "
+			   "section %s, %d maps in %zd bytes\n",
+			   obj->path, nr_maps, data->d_size);
+		return -EINVAL;
+	}
+
 	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
 	if (!obj->maps) {
 		pr_warning("alloc maps for object failed\n");
@@ -690,7 +674,7 @@ bpf_object__init_maps(struct bpf_object *obj)
 				      obj->efile.strtabidx,
 				      sym.st_name);
 		obj->maps[map_idx].offset = sym.st_value;
-		if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) {
+		if (sym.st_value + map_def_sz > data->d_size) {
 			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
 				   obj->path, map_name);
 			return -EINVAL;
@@ -704,12 +688,40 @@ bpf_object__init_maps(struct bpf_object *obj)
 		pr_debug("map %d is \"%s\"\n", map_idx,
 			 obj->maps[map_idx].name);
 		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
-		obj->maps[map_idx].def = *def;
+		/*
+		 * If the definition of the map in the object file fits in
+		 * bpf_map_def, copy it.  Any extra fields in our version
+		 * of bpf_map_def will default to zero as a result of the
+		 * calloc above.
+		 */
+		if (map_def_sz <= sizeof(struct bpf_map_def)) {
+			memcpy(&obj->maps[map_idx].def, def, map_def_sz);
+		} else {
+			/*
+			 * Here the map structure being read is bigger than what
+			 * we expect, truncate if the excess bits are all zero.
+			 * If they are not zero, reject this map as
+			 * incompatible.
+			 */
+			char *b;
+			for (b = ((char *)def) + sizeof(struct bpf_map_def);
+			     b < ((char *)def) + map_def_sz; b++) {
+				if (*b != 0) {
+					pr_warning("maps section in %s: \"%s\" "
+						   "has unrecognized, non-zero "
+						   "options\n",
+						   obj->path, map_name);
+					return -EINVAL;
+				}
+			}
+			memcpy(&obj->maps[map_idx].def, def,
+			       sizeof(struct bpf_map_def));
+		}
 		map_idx++;
 	}
 
 	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
-	return bpf_object__validate_maps(obj);
+	return 0;
 }
 
 static int bpf_object__elf_collect(struct bpf_object *obj)
-- 
cgit v1.2.3


From fe9b5f774b28143dcc2957eadffefdca6171a26a Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Thu, 5 Oct 2017 10:41:58 -0400
Subject: libbpf: use map_flags when creating maps

This is required to use BPF_MAP_TYPE_LPM_TRIE or any other map type
which requires flags.

Signed-off-by: Craig Gallek <kraig@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/lib/bpf/libbpf.c | 2 +-
 tools/lib/bpf/libbpf.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 23152890ec60..5aa45f89da93 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -942,7 +942,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 					   def->key_size,
 					   def->value_size,
 					   def->max_entries,
-					   0);
+					   def->map_flags);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7959086eb9c9..6e20003109e0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -207,6 +207,7 @@ struct bpf_map_def {
 	unsigned int key_size;
 	unsigned int value_size;
 	unsigned int max_entries;
+	unsigned int map_flags;
 };
 
 /*
-- 
cgit v1.2.3


From 06755a871314c7443a89c09650cdb3982466e1a8 Mon Sep 17 00:00:00 2001
From: Seth Forshee <seth.forshee@canonical.com>
Date: Thu, 28 Sep 2017 09:34:26 -0400
Subject: selftests/powerpc: Use snprintf to construct DSCR sysfs interface
 paths

Currently sprintf is used, and while paths should never exceed
the size of the buffer it is theoretically possible since
dirent.d_name is 256 bytes. As a result this trips
-Wformat-overflow, and since the test is built with -Wall -Werror
the causes the build to fail. Switch to using snprintf and skip
any paths which are too long for the filename buffer.

Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
index 17fb1b43c320..1899bd85121f 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
@@ -53,6 +53,8 @@ static int check_all_cpu_dscr_defaults(unsigned long val)
 	}
 
 	while ((dp = readdir(sysfs))) {
+		int len;
+
 		if (!(dp->d_type & DT_DIR))
 			continue;
 		if (!strcmp(dp->d_name, "cpuidle"))
@@ -60,7 +62,9 @@ static int check_all_cpu_dscr_defaults(unsigned long val)
 		if (!strstr(dp->d_name, "cpu"))
 			continue;
 
-		sprintf(file, "%s%s/dscr", CPU_PATH, dp->d_name);
+		len = snprintf(file, LEN_MAX, "%s%s/dscr", CPU_PATH, dp->d_name);
+		if (len >= LEN_MAX)
+			continue;
 		if (access(file, F_OK))
 			continue;
 
-- 
cgit v1.2.3


From d327a224ba2cbe234d82fd560ff8e5bb38b0bb4b Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Thu, 28 Sep 2017 15:01:44 +0200
Subject: tools: gpio: Print error string on IOCTL failures

Add to error messages the error description by concatenating
output of strerror() function to error messages print out by
gpio-utils.c on IOCTL failures.
Rationalize error messages, while at there, making all of them
look the same.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 tools/gpio/gpio-utils.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c
index b86a32d90d88..cf7e2f3419ee 100644
--- a/tools/gpio/gpio-utils.c
+++ b/tools/gpio/gpio-utils.c
@@ -76,7 +76,8 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines,
 	fd = open(chrdev_name, 0);
 	if (fd == -1) {
 		ret = -errno;
-		fprintf(stderr, "Failed to open %s\n", chrdev_name);
+		fprintf(stderr, "Failed to open %s, %s\n",
+			chrdev_name, strerror(errno));
 		goto exit_close_error;
 	}
 
@@ -92,8 +93,8 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines,
 	ret = ioctl(fd, GPIO_GET_LINEHANDLE_IOCTL, &req);
 	if (ret == -1) {
 		ret = -errno;
-		fprintf(stderr, "Failed to issue GET LINEHANDLE IOCTL (%d)\n",
-			ret);
+		fprintf(stderr, "Failed to issue %s (%d), %s\n",
+			"GPIO_GET_LINEHANDLE_IOCTL", ret, strerror(errno));
 	}
 
 exit_close_error:
@@ -118,8 +119,9 @@ int gpiotools_set_values(const int fd, struct gpiohandle_data *data)
 	ret = ioctl(fd, GPIOHANDLE_SET_LINE_VALUES_IOCTL, data);
 	if (ret == -1) {
 		ret = -errno;
-		fprintf(stderr, "Failed to issue %s (%d)\n",
-			"GPIOHANDLE_SET_LINE_VALUES_IOCTL", ret);
+		fprintf(stderr, "Failed to issue %s (%d), %s\n",
+			"GPIOHANDLE_SET_LINE_VALUES_IOCTL", ret,
+			strerror(errno));
 	}
 
 	return ret;
@@ -141,8 +143,9 @@ int gpiotools_get_values(const int fd, struct gpiohandle_data *data)
 	ret = ioctl(fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, data);
 	if (ret == -1) {
 		ret = -errno;
-		fprintf(stderr, "Failed to issue %s (%d)\n",
-			"GPIOHANDLE_GET_LINE_VALUES_IOCTL", ret);
+		fprintf(stderr, "Failed to issue %s (%d), %s\n",
+			"GPIOHANDLE_GET_LINE_VALUES_IOCTL", ret,
+			strerror(errno));
 	}
 
 	return ret;
-- 
cgit v1.2.3


From 10246dc84dfcabb05f2d29d442c9de967fd61270 Mon Sep 17 00:00:00 2001
From: Yasunori Goto <y-goto@jp.fujitsu.com>
Date: Fri, 22 Sep 2017 16:48:38 +0900
Subject: acpi nfit: nfit_test supports translate SPA

To test ndctl list which use interface of Translate SPA,
nfit_test needs to emulates it.
This test module searches region which includes SPA and
returns 1 dimm handle which is last one.

Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c | 104 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 103 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index bef419d4266d..3a3bad348d56 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -342,6 +342,84 @@ static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
 	return 0;
 }
 
+struct region_search_spa {
+	u64 addr;
+	struct nd_region *region;
+};
+
+static int is_region_device(struct device *dev)
+{
+	return !strncmp(dev->kobj.name, "region", 6);
+}
+
+static int nfit_test_search_region_spa(struct device *dev, void *data)
+{
+	struct region_search_spa *ctx = data;
+	struct nd_region *nd_region;
+	resource_size_t ndr_end;
+
+	if (!is_region_device(dev))
+		return 0;
+
+	nd_region = to_nd_region(dev);
+	ndr_end = nd_region->ndr_start + nd_region->ndr_size;
+
+	if (ctx->addr >= nd_region->ndr_start && ctx->addr < ndr_end) {
+		ctx->region = nd_region;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int nfit_test_search_spa(struct nvdimm_bus *bus,
+		struct nd_cmd_translate_spa *spa)
+{
+	int ret;
+	struct nd_region *nd_region = NULL;
+	struct nvdimm *nvdimm = NULL;
+	struct nd_mapping *nd_mapping = NULL;
+	struct region_search_spa ctx = {
+		.addr = spa->spa,
+		.region = NULL,
+	};
+	u64 dpa;
+
+	ret = device_for_each_child(&bus->dev, &ctx,
+				nfit_test_search_region_spa);
+
+	if (!ret)
+		return -ENODEV;
+
+	nd_region = ctx.region;
+
+	dpa = ctx.addr - nd_region->ndr_start;
+
+	/*
+	 * last dimm is selected for test
+	 */
+	nd_mapping = &nd_region->mapping[nd_region->ndr_mappings - 1];
+	nvdimm = nd_mapping->nvdimm;
+
+	spa->devices[0].nfit_device_handle = handle[nvdimm->id];
+	spa->num_nvdimms = 1;
+	spa->devices[0].dpa = dpa;
+
+	return 0;
+}
+
+static int nfit_test_cmd_translate_spa(struct nvdimm_bus *bus,
+		struct nd_cmd_translate_spa *spa, unsigned int buf_len)
+{
+	if (buf_len < spa->translate_length)
+		return -EINVAL;
+
+	if (nfit_test_search_spa(bus, spa) < 0 || !spa->num_nvdimms)
+		spa->status = 2;
+
+	return 0;
+}
+
 static int nfit_test_cmd_smart(struct nd_cmd_smart *smart, unsigned int buf_len)
 {
 	static const struct nd_smart_payload smart_data = {
@@ -449,6 +527,26 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		}
 	} else {
 		struct ars_state *ars_state = &t->ars_state;
+		struct nd_cmd_pkg *call_pkg = buf;
+
+		if (!nd_desc)
+			return -ENOTTY;
+
+		if (cmd == ND_CMD_CALL) {
+			func = call_pkg->nd_command;
+
+			buf_len = call_pkg->nd_size_in + call_pkg->nd_size_out;
+			buf = (void *) call_pkg->nd_payload;
+
+			switch (func) {
+			case NFIT_CMD_TRANSLATE_SPA:
+				rc = nfit_test_cmd_translate_spa(
+					acpi_desc->nvdimm_bus, buf, buf_len);
+				return rc;
+			default:
+				return -ENOTTY;
+			}
+		}
 
 		if (!nd_desc || !test_bit(cmd, &nd_desc->cmd_mask))
 			return -ENOTTY;
@@ -1430,7 +1528,9 @@ static void nfit_test0_setup(struct nfit_test *t)
 	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_CALL, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_SMART_THRESHOLD, &acpi_desc->dimm_cmd_force_en);
+	set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_nfit_cmd_force_en);
 }
 
 static void nfit_test1_setup(struct nfit_test *t)
@@ -1613,10 +1713,12 @@ static int nfit_ctl_test(struct device *dev)
 			.cmd_mask = 1UL << ND_CMD_ARS_CAP
 				| 1UL << ND_CMD_ARS_START
 				| 1UL << ND_CMD_ARS_STATUS
-				| 1UL << ND_CMD_CLEAR_ERROR,
+				| 1UL << ND_CMD_CLEAR_ERROR
+				| 1UL << ND_CMD_CALL,
 			.module = THIS_MODULE,
 			.provider_name = "ACPI.NFIT",
 			.ndctl = acpi_nfit_ctl,
+			.bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA,
 		},
 		.dev = &adev->dev,
 	};
-- 
cgit v1.2.3


From 020a32d9581ac824d038b0b4e24e977e3cc8589f Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 5 Oct 2017 09:19:21 -0700
Subject: bpf: add a test case for helper bpf_perf_event_read_value

The bpf sample program tracex6 is enhanced to use the new
helper to read enabled/running time as well.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/tracex6_kern.c                | 26 ++++++++++++++++++++++++++
 samples/bpf/tracex6_user.c                | 13 ++++++++++++-
 tools/include/uapi/linux/bpf.h            |  3 ++-
 tools/testing/selftests/bpf/bpf_helpers.h |  3 +++
 4 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
index e7d180305974..46c557afac73 100644
--- a/samples/bpf/tracex6_kern.c
+++ b/samples/bpf/tracex6_kern.c
@@ -15,6 +15,12 @@ struct bpf_map_def SEC("maps") values = {
 	.value_size = sizeof(u64),
 	.max_entries = 64,
 };
+struct bpf_map_def SEC("maps") values2 = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(int),
+	.value_size = sizeof(struct bpf_perf_event_value),
+	.max_entries = 64,
+};
 
 SEC("kprobe/htab_map_get_next_key")
 int bpf_prog1(struct pt_regs *ctx)
@@ -37,5 +43,25 @@ int bpf_prog1(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("kprobe/htab_map_lookup_elem")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	u32 key = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value *val, buf;
+	int error;
+
+	error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf));
+	if (error)
+		return 0;
+
+	val = bpf_map_lookup_elem(&values2, &key);
+	if (val)
+		*val = buf;
+	else
+		bpf_map_update_elem(&values2, &key, &buf, BPF_NOEXIST);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
index a05a99a0752f..3341a96fc046 100644
--- a/samples/bpf/tracex6_user.c
+++ b/samples/bpf/tracex6_user.c
@@ -22,6 +22,7 @@
 
 static void check_on_cpu(int cpu, struct perf_event_attr *attr)
 {
+	struct bpf_perf_event_value value2;
 	int pmu_fd, error = 0;
 	cpu_set_t set;
 	__u64 value;
@@ -46,8 +47,18 @@ static void check_on_cpu(int cpu, struct perf_event_attr *attr)
 		fprintf(stderr, "Value missing for CPU %d\n", cpu);
 		error = 1;
 		goto on_exit;
+	} else {
+		fprintf(stderr, "CPU %d: %llu\n", cpu, value);
+	}
+	/* The above bpf_map_lookup_elem should trigger the second kprobe */
+	if (bpf_map_lookup_elem(map_fd[2], &cpu, &value2)) {
+		fprintf(stderr, "Value2 missing for CPU %d\n", cpu);
+		error = 1;
+		goto on_exit;
+	} else {
+		fprintf(stderr, "CPU %d: counter: %llu, enabled: %llu, running: %llu\n", cpu,
+			value2.counter, value2.enabled, value2.running);
 	}
-	fprintf(stderr, "CPU %d: %llu\n", cpu, value);
 
 on_exit:
 	assert(bpf_map_delete_elem(map_fd[0], &cpu) == 0 || error);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cb2b9f95160a..cdf6c4f50b0f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -697,7 +697,8 @@ union bpf_attr {
 	FN(redirect_map),		\
 	FN(sk_redirect_map),		\
 	FN(sock_map_update),		\
-	FN(xdp_adjust_meta),
+	FN(xdp_adjust_meta),		\
+	FN(perf_event_read_value),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index a56053db26f5..c15ca83dbbd9 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -72,6 +72,9 @@ static int (*bpf_sk_redirect_map)(void *map, int key, int flags) =
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 				  unsigned long long flags) =
 	(void *) BPF_FUNC_sock_map_update;
+static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
+					void *buf, unsigned int buf_size) =
+	(void *) BPF_FUNC_perf_event_read_value;
 
 
 /* llvm builtin functions that eBPF C program may use to
-- 
cgit v1.2.3


From 81b9cf8028a17bdbdaa0da80b735b32150d4e89e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 5 Oct 2017 09:19:23 -0700
Subject: bpf: add a test case for helper bpf_perf_prog_read_value

The bpf sample program trace_event is enhanced to use the new
helper to print out enabled/running time.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/trace_event_kern.c            | 10 ++++++++++
 samples/bpf/trace_event_user.c            | 13 ++++++++-----
 tools/include/uapi/linux/bpf.h            |  3 ++-
 tools/testing/selftests/bpf/bpf_helpers.h |  3 +++
 4 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c
index 41b6115a32eb..a77a583d94d4 100644
--- a/samples/bpf/trace_event_kern.c
+++ b/samples/bpf/trace_event_kern.c
@@ -37,10 +37,14 @@ struct bpf_map_def SEC("maps") stackmap = {
 SEC("perf_event")
 int bpf_prog1(struct bpf_perf_event_data *ctx)
 {
+	char time_fmt1[] = "Time Enabled: %llu, Time Running: %llu";
+	char time_fmt2[] = "Get Time Failed, ErrCode: %d";
 	char fmt[] = "CPU-%d period %lld ip %llx";
 	u32 cpu = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value value_buf;
 	struct key_t key;
 	u64 *val, one = 1;
+	int ret;
 
 	if (ctx->sample_period < 10000)
 		/* ignore warmup */
@@ -54,6 +58,12 @@ int bpf_prog1(struct bpf_perf_event_data *ctx)
 		return 0;
 	}
 
+	ret = bpf_perf_prog_read_value(ctx, (void *)&value_buf, sizeof(struct bpf_perf_event_value));
+	if (!ret)
+	  bpf_trace_printk(time_fmt1, sizeof(time_fmt1), value_buf.enabled, value_buf.running);
+	else
+	  bpf_trace_printk(time_fmt2, sizeof(time_fmt2), ret);
+
 	val = bpf_map_lookup_elem(&counts, &key);
 	if (val)
 		(*val)++;
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 7bd827b84a67..bf4f1b6d9a52 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -127,6 +127,9 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 	int *pmu_fd = malloc(nr_cpus * sizeof(int));
 	int i, error = 0;
 
+	/* system wide perf event, no need to inherit */
+	attr->inherit = 0;
+
 	/* open perf_event on all cpus */
 	for (i = 0; i < nr_cpus; i++) {
 		pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0);
@@ -154,6 +157,11 @@ static void test_perf_event_task(struct perf_event_attr *attr)
 {
 	int pmu_fd;
 
+	/* per task perf event, enable inherit so the "dd ..." command can be traced properly.
+	 * Enabling inherit will cause bpf_perf_prog_read_time helper failure.
+	 */
+	attr->inherit = 1;
+
 	/* open task bound event */
 	pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0);
 	if (pmu_fd < 0) {
@@ -175,14 +183,12 @@ static void test_bpf_perf_event(void)
 		.freq = 1,
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_type_sw = {
 		.sample_freq = SAMPLE_FREQ,
 		.freq = 1,
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_hw_cache_l1d = {
 		.sample_freq = SAMPLE_FREQ,
@@ -192,7 +198,6 @@ static void test_bpf_perf_event(void)
 			PERF_COUNT_HW_CACHE_L1D |
 			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
 			(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_hw_cache_branch_miss = {
 		.sample_freq = SAMPLE_FREQ,
@@ -202,7 +207,6 @@ static void test_bpf_perf_event(void)
 			PERF_COUNT_HW_CACHE_BPU |
 			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
 			(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_type_raw = {
 		.sample_freq = SAMPLE_FREQ,
@@ -210,7 +214,6 @@ static void test_bpf_perf_event(void)
 		.type = PERF_TYPE_RAW,
 		/* Intel Instruction Retired */
 		.config = 0xc0,
-		.inherit = 1,
 	};
 
 	printf("Test HW_CPU_CYCLES\n");
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cdf6c4f50b0f..0894fd20b12b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -698,7 +698,8 @@ union bpf_attr {
 	FN(sk_redirect_map),		\
 	FN(sock_map_update),		\
 	FN(xdp_adjust_meta),		\
-	FN(perf_event_read_value),
+	FN(perf_event_read_value),	\
+	FN(perf_prog_read_value),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index c15ca83dbbd9..e25dbf6038cf 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -75,6 +75,9 @@ static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
 					void *buf, unsigned int buf_size) =
 	(void *) BPF_FUNC_perf_event_read_value;
+static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
+				       unsigned int buf_size) =
+	(void *) BPF_FUNC_perf_prog_read_value;
 
 
 /* llvm builtin functions that eBPF C program may use to
-- 
cgit v1.2.3


From 067cae47771c864604969fd902efe10916e0d79c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 5 Oct 2017 21:52:12 -0700
Subject: bpf: Use char in prog and map name

Instead of u8, use char for prog and map name.  It can avoid the
userspace tool getting compiler's signess warning.  The
bpf_prog_aux, bpf_map, bpf_attr, bpf_prog_info and
bpf_map_info are changed.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h            | 4 ++--
 include/uapi/linux/bpf.h       | 8 ++++----
 tools/include/uapi/linux/bpf.h | 8 ++++----
 3 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a67daea731ab..bc7da2ddfcaf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -56,7 +56,7 @@ struct bpf_map {
 	struct work_struct work;
 	atomic_t usercnt;
 	struct bpf_map *inner_map_meta;
-	u8 name[BPF_OBJ_NAME_LEN];
+	char name[BPF_OBJ_NAME_LEN];
 };
 
 /* function argument constraints */
@@ -189,7 +189,7 @@ struct bpf_prog_aux {
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
-	u8 name[BPF_OBJ_NAME_LEN];
+	char name[BPF_OBJ_NAME_LEN];
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5bbbec17aa5a..6db9e1d679cd 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -230,7 +230,7 @@ union bpf_attr {
 		__u32	numa_node;	/* numa node (effective only if
 					 * BPF_F_NUMA_NODE is set).
 					 */
-		__u8	map_name[BPF_OBJ_NAME_LEN];
+		char	map_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -253,7 +253,7 @@ union bpf_attr {
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
-		__u8		prog_name[BPF_OBJ_NAME_LEN];
+		char		prog_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -888,7 +888,7 @@ struct bpf_prog_info {
 	__u32 created_by_uid;
 	__u32 nr_map_ids;
 	__aligned_u64 map_ids;
-	__u8  name[BPF_OBJ_NAME_LEN];
+	char name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -898,7 +898,7 @@ struct bpf_map_info {
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 map_flags;
-	__u8  name[BPF_OBJ_NAME_LEN];
+	char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0894fd20b12b..fb4fb81ce5b0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -230,7 +230,7 @@ union bpf_attr {
 		__u32	numa_node;	/* numa node (effective only if
 					 * BPF_F_NUMA_NODE is set).
 					 */
-		__u8	map_name[BPF_OBJ_NAME_LEN];
+		char	map_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -253,7 +253,7 @@ union bpf_attr {
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
-		__u8		prog_name[BPF_OBJ_NAME_LEN];
+		char		prog_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -871,7 +871,7 @@ struct bpf_prog_info {
 	__u32 created_by_uid;
 	__u32 nr_map_ids;
 	__aligned_u64 map_ids;
-	__u8  name[BPF_OBJ_NAME_LEN];
+	char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -881,7 +881,7 @@ struct bpf_map_info {
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 map_flags;
-	__u8  name[BPF_OBJ_NAME_LEN];
+	char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
-- 
cgit v1.2.3


From a99ca6dbf429fe6c035cfb880d91bf6a223fcd3c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 9 Oct 2017 10:30:09 -0700
Subject: selftests/bpf: add a test for verifier logs

Add a test for verifier log handling.  Check bad attr combinations
but focus on cases when log is truncated.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/Makefile            |   2 +-
 tools/testing/selftests/bpf/test_verifier_log.c | 171 ++++++++++++++++++++++++
 2 files changed, 172 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_verifier_log.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 924af8d79bde..2e7880ea0add 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -12,7 +12,7 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i
 LDLIBS += -lcap -lelf
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align
+	test_align test_verifier_log
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c
new file mode 100644
index 000000000000..3cc0b561489e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_verifier_log.c
@@ -0,0 +1,171 @@
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+
+#include <bpf/bpf.h>
+
+#define LOG_SIZE (1 << 20)
+
+#define err(str...)	printf("ERROR: " str)
+
+static const struct bpf_insn code_sample[] = {
+	/* We need a few instructions to pass the min log length */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+		     BPF_FUNC_map_lookup_elem),
+	BPF_EXIT_INSN(),
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
+static int load(char *log, size_t log_len, int log_level)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn));
+	attr.insns = ptr_to_u64(code_sample);
+	attr.license = ptr_to_u64("GPL");
+	attr.log_buf = ptr_to_u64(log);
+	attr.log_size = log_len;
+	attr.log_level = log_level;
+
+	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
+static void check_ret(int ret, int exp_errno)
+{
+	if (ret > 0) {
+		close(ret);
+		err("broken sample loaded successfully!?\n");
+		exit(1);
+	}
+
+	if (!ret || errno != exp_errno) {
+		err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n",
+		    ret, errno, -1, exp_errno);
+		exit(1);
+	}
+}
+
+static void check_ones(const char *buf, size_t len, const char *msg)
+{
+	while (len--)
+		if (buf[len] != 1) {
+			err("%s", msg);
+			exit(1);
+		}
+}
+
+static void test_log_good(char *log, size_t buf_len, size_t log_len,
+			  size_t exp_len, int exp_errno, const char *full_log)
+{
+	size_t len;
+	int ret;
+
+	memset(log, 1, buf_len);
+
+	ret = load(log, log_len, 1);
+	check_ret(ret, exp_errno);
+
+	len = strnlen(log, buf_len);
+	if (len == buf_len) {
+		err("verifier did not NULL terminate the log\n");
+		exit(1);
+	}
+	if (exp_len && len != exp_len) {
+		err("incorrect log length expected:%zd have:%zd\n",
+		    exp_len, len);
+		exit(1);
+	}
+
+	if (strchr(log, 1)) {
+		err("verifier leaked a byte through\n");
+		exit(1);
+	}
+
+	check_ones(log + len + 1, buf_len - len - 1,
+		   "verifier wrote bytes past NULL termination\n");
+
+	if (memcmp(full_log, log, LOG_SIZE)) {
+		err("log did not match expected output\n");
+		exit(1);
+	}
+}
+
+static void test_log_bad(char *log, size_t log_len, int log_level)
+{
+	int ret;
+
+	ret = load(log, log_len, log_level);
+	check_ret(ret, EINVAL);
+	if (log)
+		check_ones(log, LOG_SIZE,
+			   "verifier touched log with bad parameters\n");
+}
+
+int main(int argc, char **argv)
+{
+	char full_log[LOG_SIZE];
+	char log[LOG_SIZE];
+	size_t want_len;
+	int i;
+
+	memset(log, 1, LOG_SIZE);
+
+	/* Test incorrect attr */
+	printf("Test log_level 0...\n");
+	test_log_bad(log, LOG_SIZE, 0);
+
+	printf("Test log_size < 128...\n");
+	test_log_bad(log, 15, 1);
+
+	printf("Test log_buff = NULL...\n");
+	test_log_bad(NULL, LOG_SIZE, 1);
+
+	/* Test with log big enough */
+	printf("Test oversized buffer...\n");
+	test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log);
+
+	want_len = strlen(full_log);
+
+	printf("Test exact buffer...\n");
+	test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log);
+
+	printf("Test undersized buffers...\n");
+	for (i = 0; i < 64; i++) {
+		full_log[want_len - i + 1] = 1;
+		full_log[want_len - i] = 0;
+
+		test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i,
+			      ENOSPC, full_log);
+	}
+
+	printf("test_verifier_log: OK\n");
+	return 0;
+}
-- 
cgit v1.2.3


From c9c35995bcf812ee8136f634c25bc6ccc3021d4c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 9 Oct 2017 10:30:13 -0700
Subject: tools: bpftool: use the kernel's instruction printer

Compile the instruction printer from kernel/bpf and use it
for disassembling "translated" eBPF code.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 11 +++---
 tools/bpf/bpftool/Makefile                       |  7 ++--
 tools/bpf/bpftool/main.h                         | 10 ++----
 tools/bpf/bpftool/prog.c                         | 44 +++++++++++++++++++-----
 4 files changed, 51 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 57fc4b9924ea..04d12f768f06 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -11,7 +11,7 @@ SYNOPSIS
 ========
 
 |	**bpftool** prog show [*PROG*]
-|	**bpftool** prog dump xlated *PROG*  file *FILE*
+|	**bpftool** prog dump xlated *PROG* [file *FILE*] [opcodes]
 |	**bpftool** prog dump jited  *PROG* [file *FILE*] [opcodes]
 |	**bpftool** prog pin *PROG* *FILE*
 |	**bpftool** prog help
@@ -28,9 +28,12 @@ DESCRIPTION
 		  Output will start with program ID followed by program type and
 		  zero or more named attributes (depending on kernel version).
 
-	**bpftool prog dump xlated** *PROG*  **file** *FILE*
-		  Dump eBPF instructions of the program from the kernel to a
-		  file.
+	**bpftool prog dump xlated** *PROG* [**file** *FILE*] [**opcodes**]
+		  Dump eBPF instructions of the program from the kernel.
+		  If *FILE* is specified image will be written to a file,
+		  otherwise it will be disassembled and printed to stdout.
+
+		  **opcodes** controls if raw opcodes will be printed.
 
 	**bpftool prog dump jited**  *PROG* [**file** *FILE*] [**opcodes**]
 		  Dump jited image (host machine code) of the program.
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 8705ee44664d..4f339824ca57 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -51,7 +51,7 @@ CC = gcc
 
 CFLAGS += -O2
 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow
-CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf
+CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/
 LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
 
 include $(wildcard *.d)
@@ -59,7 +59,10 @@ include $(wildcard *.d)
 all: $(OUTPUT)bpftool
 
 SRCS=$(wildcard *.c)
-OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS))
+OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+
+$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
+	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
 
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 85d2d7870a58..8e809b2bb311 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -36,11 +36,12 @@
 #ifndef __BPF_TOOL_H
 #define __BPF_TOOL_H
 
+/* BFD and kernel.h both define GCC_VERSION, differently */
+#undef GCC_VERSION
 #include <stdbool.h>
 #include <stdio.h>
 #include <linux/bpf.h>
-
-#define ARRAY_SIZE(a)	(sizeof(a) / sizeof(a[0]))
+#include <linux/kernel.h>
 
 #define err(msg...)	fprintf(stderr, "Error: " msg)
 #define warn(msg...)	fprintf(stderr, "Warning: " msg)
@@ -48,11 +49,6 @@
 
 #define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
 
-#define min(a, b)							\
-	({ typeof(a) _a = (a); typeof(b) _b = (b); _a > _b ? _b : _a; })
-#define max(a, b)							\
-	({ typeof(a) _a = (a); typeof(b) _b = (b); _a < _b ? _b : _a; })
-
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
 #define BAD_ARG()	({ err("what is '%s'?\n", *argv); -1; })
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 421ba89ce86a..9e2681c83717 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -35,6 +35,7 @@
 
 #include <errno.h>
 #include <fcntl.h>
+#include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -46,6 +47,7 @@
 #include <bpf.h>
 
 #include "main.h"
+#include "disasm.h"
 
 static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_UNSPEC]		= "unspec",
@@ -297,11 +299,39 @@ static int do_show(int argc, char **argv)
 	return 0;
 }
 
+static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vprintf(fmt, args);
+	va_end(args);
+}
+
+static void dump_xlated(void *buf, unsigned int len, bool opcodes)
+{
+	struct bpf_insn *insn = buf;
+	unsigned int i;
+
+	for (i = 0; i < len / sizeof(*insn); i++) {
+		printf("% 4d: ", i);
+		print_bpf_insn(print_insn, NULL, insn + i, true);
+
+		if (opcodes) {
+			printf("       ");
+			print_hex(insn + i, 8, " ");
+			printf("\n");
+		}
+
+		if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW))
+			i++;
+	}
+}
+
 static int do_dump(int argc, char **argv)
 {
 	struct bpf_prog_info info = {};
 	__u32 len = sizeof(info);
-	bool can_disasm = false;
 	unsigned int buf_size;
 	char *filepath = NULL;
 	bool opcodes = false;
@@ -315,7 +345,6 @@ static int do_dump(int argc, char **argv)
 	if (is_prefix(*argv, "jited")) {
 		member_len = &info.jited_prog_len;
 		member_ptr = &info.jited_prog_insns;
-		can_disasm = true;
 	} else if (is_prefix(*argv, "xlated")) {
 		member_len = &info.xlated_prog_len;
 		member_ptr = &info.xlated_prog_insns;
@@ -346,10 +375,6 @@ static int do_dump(int argc, char **argv)
 		NEXT_ARG();
 	}
 
-	if (!filepath && !can_disasm) {
-		err("expected 'file' got %s\n", *argv);
-		return -1;
-	}
 	if (argc) {
 		usage();
 		return -1;
@@ -409,7 +434,10 @@ static int do_dump(int argc, char **argv)
 			goto err_free;
 		}
 	} else {
-		disasm_print_insn(buf, *member_len, opcodes);
+		if (member_len == &info.jited_prog_len)
+			disasm_print_insn(buf, *member_len, opcodes);
+		else
+			dump_xlated(buf, *member_len, opcodes);
 	}
 
 	free(buf);
@@ -430,7 +458,7 @@ static int do_help(int argc, char **argv)
 {
 	fprintf(stderr,
 		"Usage: %s %s show [PROG]\n"
-		"       %s %s dump xlated PROG  file FILE\n"
+		"       %s %s dump xlated PROG [file FILE] [opcodes]\n"
 		"       %s %s dump jited  PROG [file FILE] [opcodes]\n"
 		"       %s %s pin   PROG FILE\n"
 		"       %s %s help\n"
-- 
cgit v1.2.3


From 8f88f74a1641f57607a2417669e0e02b768796b4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 10 Oct 2017 16:18:05 +0200
Subject: selftests: rtnetlink: test RTM_GETNETCONF

exercise RTM_GETNETCONF call path for unspec, inet and inet6
families, they are DOIT_UNLOCKED candidates.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index e8c86c416ed0..a8a8cdf726b2 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -37,6 +37,26 @@ kci_del_dummy()
 	check_err $?
 }
 
+kci_test_netconf()
+{
+	dev="$1"
+	r=$ret
+
+	ip netconf show dev "$dev" > /dev/null
+	check_err $?
+
+	for f in 4 6; do
+		ip -$f netconf show dev "$dev" > /dev/null
+		check_err $?
+	done
+
+	if [ $ret -ne 0 ] ;then
+		echo "FAIL: ip netconf show $dev"
+		test $r -eq 0 && ret=0
+		return 1
+	fi
+}
+
 # add a bridge with vlans on top
 kci_test_bridge()
 {
@@ -63,6 +83,11 @@ kci_test_bridge()
 	check_err $?
 	ip r s t all > /dev/null
 	check_err $?
+
+	for name in "$devbr" "$vlandev" "$devdummy" ; do
+		kci_test_netconf "$name"
+	done
+
 	ip -6 addr del dev "$vlandev" dead:42::1234/64
 	check_err $?
 
@@ -100,6 +125,9 @@ kci_test_gre()
 	check_err $?
 	ip addr > /dev/null
 	check_err $?
+
+	kci_test_netconf "$gredev"
+
 	ip addr del dev "$devdummy" 10.23.7.11/24
 	check_err $?
 
-- 
cgit v1.2.3


From 9cc5fbbb8ca2178d94f2eeeb2ce675293a3f8ae2 Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jeremy@jcline.org>
Date: Wed, 4 Oct 2017 03:08:11 +0000
Subject: tools/kvm_stat: Add Python 3 support to kvm_stat
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make kvm_stat support Python 3 by changing the use of "print" to a
function rather than a statement, switching from "iteritems" and
"iterkeys" (removed in Python 3) to "items" and "keys" respectively,
and decoding bytes to strings when dealing with text.

With this change, kvm_stat is usable with Python 2.6 and greater.

Signed-off-by: Jeremy Cline <jeremy@jcline.org>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 tools/kvm/kvm_stat/kvm_stat | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 32283d88701a..217cf6f95c36 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -19,9 +19,11 @@ Three different ways of output formatting are available:
 
 The data is sampled from the KVM's debugfs entries and its perf events.
 """
+from __future__ import print_function
 
 import curses
 import sys
+import locale
 import os
 import time
 import optparse
@@ -225,6 +227,8 @@ IOCTL_NUMBERS = {
     'RESET':       0x00002403,
 }
 
+ENCODING = locale.getpreferredencoding(False)
+
 
 class Arch(object):
     """Encapsulates global architecture specific data.
@@ -666,7 +670,7 @@ class TracepointProvider(Provider):
         """Returns 'event name: current value' for all enabled events."""
         ret = defaultdict(int)
         for group in self.group_leaders:
-            for name, val in group.read().iteritems():
+            for name, val in group.read().items():
                 if name in self._fields:
                     ret[name] += val
         return ret
@@ -955,7 +959,7 @@ class Tui(object):
         except:
             raise Exception
         for line in child.stdout:
-            line = line.lstrip().split(' ', 1)
+            line = line.decode(ENCODING).lstrip().split(' ', 1)
             # perform a sanity check before calling the more expensive
             # function to possibly extract the guest name
             if ' -name ' in line[1]:
@@ -1005,7 +1009,7 @@ class Tui(object):
         name = ''
         try:
             line = open('/proc/{}/cmdline'
-                        .format(pid), 'rb').read().split('\0')
+                        .format(pid), 'r').read().split('\0')
             parms = line[line.index('-name') + 1].split(',')
             while '' in parms:
                 # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results
@@ -1170,7 +1174,7 @@ class Tui(object):
                                .format(self.stats.fields_filter))
             self.screen.addstr(3, 0, "New regex: ")
             curses.echo()
-            regex = self.screen.getstr()
+            regex = self.screen.getstr().decode(ENCODING)
             curses.noecho()
             if len(regex) == 0:
                 self.stats.fields_filter = DEFAULT_REGEX
@@ -1204,7 +1208,7 @@ class Tui(object):
 
             curses.echo()
             self.screen.addstr(3, 0, "Pid [0 or pid]: ")
-            pid = self.screen.getstr()
+            pid = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
             try:
@@ -1233,7 +1237,7 @@ class Tui(object):
             self.screen.addstr(2, 0, 'Change delay from %.1fs to ' %
                                self._delay_regular)
             curses.echo()
-            val = self.screen.getstr()
+            val = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
             try:
@@ -1273,7 +1277,7 @@ class Tui(object):
             self.print_all_gnames(7)
             curses.echo()
             self.screen.addstr(3, 0, "Guest [ENTER or guest]: ")
-            gname = self.screen.getstr()
+            gname = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
             if not gname:
@@ -1369,25 +1373,25 @@ def batch(stats):
         s = stats.get()
         for key in sorted(s.keys()):
             values = s[key]
-            print '%-42s%10d%10d' % (key, values[0], values[1])
+            print('%-42s%10d%10d' % (key, values[0], values[1]))
     except KeyboardInterrupt:
         pass
 
 
 def log(stats):
     """Prints statistics as reiterating key block, multiple value blocks."""
-    keys = sorted(stats.get().iterkeys())
+    keys = sorted(stats.get().keys())
 
     def banner():
         for k in keys:
-            print '%s' % k,
-        print
+            print(k, end=' ')
+        print()
 
     def statline():
         s = stats.get()
         for k in keys:
-            print ' %9d' % s[k][1],
-        print
+            print(' %9d' % s[k][1], end=' ')
+        print()
     line = 0
     banner_repeat = 20
     while True:
-- 
cgit v1.2.3


From 2d0d21c12dfa3851620f1fa9fe2d444538f1fad4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 12 Oct 2017 11:11:22 +0200
Subject: selftests: rtnetlink: add a small macsec test case

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 42 ++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a8a8cdf726b2..5215493166c9 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -461,6 +461,47 @@ kci_test_encap()
 	ip netns del "$testns"
 }
 
+kci_test_macsec()
+{
+	msname="test_macsec0"
+	ret=0
+
+	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
+	if [ $? -ne 0 ]; then
+		echo "SKIP: macsec: iproute2 too old"
+		return 0
+	fi
+
+	ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
+	check_err $?
+	if [ $ret -ne 0 ];then
+		echo "FAIL: can't add macsec interface, skipping test"
+		return 1
+	fi
+
+	ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+	check_err $?
+
+	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
+	check_err $?
+
+	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef
+	check_err $?
+
+	ip macsec show > /dev/null
+	check_err $?
+
+	ip link del dev "$msname"
+	check_err $?
+
+	if [ $ret -ne 0 ];then
+		echo "FAIL: macsec"
+		return 1
+	fi
+
+	echo "PASS: macsec"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -478,6 +519,7 @@ kci_test_rtnl()
 	kci_test_ifalias
 	kci_test_vrf
 	kci_test_encap
+	kci_test_macsec
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From 89aca4753eb451a48f65a12b02640365dba3d4ea Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Tue, 4 Jul 2017 11:21:15 +1000
Subject: selftests/powerpc: context_switch: Fix pthread errors

Turns out pthreads returns an errno and doesn't set errno. This doesn't
play well with perror().

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 .../selftests/powerpc/benchmarks/context_switch.c       | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index f4241339edd2..87f1f0252299 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -10,6 +10,7 @@
  */
 
 #define _GNU_SOURCE
+#include <errno.h>
 #include <sched.h>
 #include <string.h>
 #include <stdio.h>
@@ -75,6 +76,7 @@ static void touch(void)
 
 static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 {
+	int rc;
 	pthread_t tid;
 	cpu_set_t cpuset;
 	pthread_attr_t attr;
@@ -82,14 +84,23 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 	CPU_ZERO(&cpuset);
 	CPU_SET(cpu, &cpuset);
 
-	pthread_attr_init(&attr);
+	rc = pthread_attr_init(&attr);
+	if (rc) {
+		errno = rc;
+		perror("pthread_attr_init");
+		exit(1);
+	}
 
-	if (pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset)) {
+	rc = pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+	if (rc)	{
+		errno = rc;
 		perror("pthread_attr_setaffinity_np");
 		exit(1);
 	}
 
-	if (pthread_create(&tid, &attr, fn, arg)) {
+	rc = pthread_create(&tid, &attr, fn, arg);
+	if (rc) {
+		errno = rc;
 		perror("pthread_create");
 		exit(1);
 	}
-- 
cgit v1.2.3


From ae3c33c157565301544570ff3476280279d43d7f Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Fri, 13 Oct 2017 17:51:22 -0400
Subject: tc-testing: Add test cases for flushing actions

Tests for flushing gact and mirred were missing. This patch
adds test cases to explicitly test the flush of any installed
gact/mirred actions.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/tests.json         | 49 +++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
index 6973bdc5b5bf..2ea00652f9ab 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
@@ -245,6 +245,27 @@
             "$TC actions flush action gact"
         ]
     },
+    {
+        "id": "3edf",
+        "name": "Flush gact actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions flush action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "0",
+        "teardown": []
+    },
     {
         "id": "63ec",
         "name": "Delete pass action",
@@ -468,6 +489,32 @@
             "$TC actions flush action mirred"
         ]
     },
+    {
+        "id": "58c3",
+        "name": "Flush mirred actions",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 1 dev lo",
+            "$TC actions add action mirred egress redirect index 2 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions show action mirred",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "[Mirror|Redirect] to device lo",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
     {
         "id": "d7c0",
         "name": "Add invalid mirred direction",
@@ -1162,4 +1209,4 @@
             "$TC actions flush action ife"
         ]
     }
-]
\ No newline at end of file
+]
-- 
cgit v1.2.3


From 0923edf456fbd6c75031ad48ad14897a6b912954 Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Fri, 13 Oct 2017 17:51:23 -0400
Subject: tc-testing: Split test case files into smaller chunks

The original submission had the test cases stored in one
monolithic file. This can be unwieldy to edit, especially as more
test cases are added. This patch removes the original tests.json
file in favour of individual ones broken down by category.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/gact.json          |  469 ++++++++
 .../selftests/tc-testing/tc-tests/actions/ife.json |   52 +
 .../tc-testing/tc-tests/actions/mirred.json        |  223 ++++
 .../tc-testing/tc-tests/actions/simple.json        |  130 +++
 .../tc-testing/tc-tests/actions/skbedit.json       |  320 ++++++
 .../tc-testing/tc-tests/actions/tests.json         | 1212 --------------------
 6 files changed, 1194 insertions(+), 1212 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
 delete mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/tests.json

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
new file mode 100644
index 000000000000..e2187b6e0b7a
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -0,0 +1,469 @@
+[
+    {
+        "id": "e89a",
+        "name": "Add valid pass action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pass index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "a02c",
+        "name": "Add valid pipe action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pipe index 6",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "feef",
+        "name": "Add valid reclassify action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action reclassify index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "8a7a",
+        "name": "Add valid drop action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 30",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "9a52",
+        "name": "Add valid continue action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action continue index 432",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "d700",
+        "name": "Add invalid action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pump index 386",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action.*index 386 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "9215",
+        "name": "Add action with duplicate index",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pipe index 15"
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 15",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "798e",
+        "name": "Add action with index exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 4294967296",
+        "expExitCode": "255",
+        "verifyCmd": "actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "22be",
+        "name": "Add action with index at 32-bit maximum",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "ac2a",
+        "name": "List actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions list action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "5",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "3edf",
+        "name": "Flush gact actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions flush action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "0",
+        "teardown": []
+    },
+    {
+        "id": "63ec",
+        "name": "Delete pass action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pass index 1"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "46be",
+        "name": "Delete pipe action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pipe index 9"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 9",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "2e08",
+        "name": "Delete reclassify action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action reclassify index 65536"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 65536",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "99c4",
+        "name": "Delete drop action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 16"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 16",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "fb6b",
+        "name": "Delete continue action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action continue index 32"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 32",
+        "expExitCode": "0",
+        "verifyCmd": "actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "0eb3",
+        "name": "Delete non-existent action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "f02c",
+        "name": "Replace gact action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 10",
+            "$TC actions add action drop index 12"
+        ],
+        "cmdUnderTest": "$TC actions replace action ok index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action gact",
+        "matchPattern": "action order [0-9]*: gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "525f",
+        "name": "Get gact action by index",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 3900800700"
+        ],
+        "cmdUnderTest": "$TC actions get action gact index 3900800700",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action gact index 3900800700",
+        "matchPattern": "index 3900800700",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
new file mode 100644
index 000000000000..9f34f0753969
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -0,0 +1,52 @@
+[
+    {
+        "id": "a568",
+        "name": "Add action with ife type",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode type 0xDEAD index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action ife index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action ife index 1",
+        "matchPattern": "type 0xDEAD",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    },
+    {
+        "id": "b983",
+        "name": "Add action without ife type",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action ife index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action ife index 1",
+        "matchPattern": "type 0xED3E",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
new file mode 100644
index 000000000000..0fcccf18399b
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -0,0 +1,223 @@
+[
+    {
+        "id": "5124",
+        "name": "Add mirred mirror to egress action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "6fb4",
+        "name": "Add mirred redirect to egress action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "ba38",
+        "name": "Get mirred actions",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 1 dev lo",
+            "$TC actions add action mirred egress redirect index 2 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions show action mirred",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "[Mirror|Redirect] to device lo",
+        "matchCount": "2",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "d7c0",
+        "name": "Add invalid mirred direction",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "e213",
+        "name": "Add invalid mirred action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "2d89",
+        "name": "Add mirred action with invalid device",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "300b",
+        "name": "Add mirred action with duplicate index",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress redirect index 15 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "a70e",
+        "name": "Delete mirred mirror action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 5 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions del action mirred index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "3fb3",
+        "name": "Delete mirred redirect action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress redirect index 5 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions del action mirred index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
new file mode 100644
index 000000000000..e89a7aa4012d
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -0,0 +1,130 @@
+[
+    {
+        "id": "b078",
+        "name": "Add simple action",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "6d4c",
+        "name": "Add simple action with duplicate index",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Aruba\" index 4"
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "2542",
+        "name": "List simple actions",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Rock\"",
+            "$TC actions add action simple sdata \"Paper\"",
+            "$TC actions add action simple sdata \"Scissors\" index 98"
+        ],
+        "cmdUnderTest": "$TC actions list action simple",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
+        "matchCount": "3",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "ea67",
+        "name": "Delete simple action",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Blinkenlights\" index 1"
+        ],
+        "cmdUnderTest": "$TC actions delete action simple index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "8ff1",
+        "name": "Flush simple actions",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Kirk\"",
+            "$TC actions add action simple sdata \"Spock\" index 50",
+            "$TC actions add action simple sdata \"McCoy\" index 9"
+        ],
+        "cmdUnderTest": "$TC actions flush action simple",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
+        "matchCount": "0",
+        "teardown": [
+            ""
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
new file mode 100644
index 000000000000..99635ea4722e
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -0,0 +1,320 @@
+[
+    {
+        "id": "6236",
+        "name": "Add skbedit action with valid mark",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "407b",
+        "name": "Add skbedit action with invalid mark",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 666777888999",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "081d",
+        "name": "Add skbedit action with priority",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit prio 99",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit priority :99",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "cc37",
+        "name": "Add skbedit action with invalid priority",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit prio foo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit priority",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "3c95",
+        "name": "Add skbedit action with queue_mapping",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "985c",
+        "name": "Add skbedit action with invalid queue_mapping",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit queue_mapping",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "224f",
+        "name": "Add skbedit action with ptype host",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype host",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype host",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "d1a3",
+        "name": "Add skbedit action with ptype otherhost",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "b9c6",
+        "name": "Add skbedit action with invalid ptype",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype openair",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype openair",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "5172",
+        "name": "List skbedit actions",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit ptype otherhost",
+            "$TC actions add action skbedit ptype broadcast",
+            "$TC actions add action skbedit mark 59",
+            "$TC actions add action skbedit mark 409"
+        ],
+        "cmdUnderTest": "$TC actions list action skbedit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchCount": "4",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "a6d6",
+        "name": "Add skbedit action with index",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "index 4040404040",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "38f3",
+        "name": "Delete skbedit action",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit mark 42 index 9009"
+        ],
+        "cmdUnderTest": "$TC actions del action skbedit index 9009",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark 42",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "ce97",
+        "name": "Flush skbedit actions",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            "$TC actions add action skbedit mark 500",
+            "$TC actions add action skbedit mark 501",
+            "$TC actions add action skbedit mark 502",
+            "$TC actions add action skbedit mark 503",
+            "$TC actions add action skbedit mark 504",
+            "$TC actions add action skbedit mark 505",
+            "$TC actions add action skbedit mark 506"
+        ],
+        "cmdUnderTest": "$TC actions flush action skbedit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
deleted file mode 100644
index 2ea00652f9ab..000000000000
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
+++ /dev/null
@@ -1,1212 +0,0 @@
-[
-    {
-        "id": "e89a",
-        "name": "Add valid pass action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pass index 8",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "a02c",
-        "name": "Add valid pipe action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pipe index 6",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "feef",
-        "name": "Add valid reclassify action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action reclassify index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "8a7a",
-        "name": "Add valid drop action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 30",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "9a52",
-        "name": "Add valid continue action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action continue index 432",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "d700",
-        "name": "Add invalid action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pump index 386",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action.*index 386 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "9215",
-        "name": "Add action with duplicate index",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pipe index 15"
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 15",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "798e",
-        "name": "Add action with index exceeding 32-bit maximum",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 4294967296",
-        "expExitCode": "255",
-        "verifyCmd": "actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "22be",
-        "name": "Add action with index at 32-bit maximum",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 4294967295",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "ac2a",
-        "name": "List actions",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action reclassify index 101",
-            "$TC actions add action reclassify index 102",
-            "$TC actions add action reclassify index 103",
-            "$TC actions add action reclassify index 104",
-            "$TC actions add action reclassify index 105"
-        ],
-        "cmdUnderTest": "$TC actions list action gact",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify",
-        "matchCount": "5",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "3edf",
-        "name": "Flush gact actions",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            "$TC actions add action reclassify index 101",
-            "$TC actions add action reclassify index 102",
-            "$TC actions add action reclassify index 103",
-            "$TC actions add action reclassify index 104",
-            "$TC actions add action reclassify index 105"
-        ],
-        "cmdUnderTest": "$TC actions flush action gact",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify",
-        "matchCount": "0",
-        "teardown": []
-    },
-    {
-        "id": "63ec",
-        "name": "Delete pass action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pass index 1"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "46be",
-        "name": "Delete pipe action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pipe index 9"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 9",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "2e08",
-        "name": "Delete reclassify action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action reclassify index 65536"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 65536",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "99c4",
-        "name": "Delete drop action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 16"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 16",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "fb6b",
-        "name": "Delete continue action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action continue index 32"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 32",
-        "expExitCode": "0",
-        "verifyCmd": "actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "0eb3",
-        "name": "Delete non-existent action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 2",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "5124",
-        "name": "Add mirred mirror to egress action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "6fb4",
-        "name": "Add mirred redirect to egress action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "ba38",
-        "name": "Get mirred actions",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 1 dev lo",
-            "$TC actions add action mirred egress redirect index 2 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions show action mirred",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "[Mirror|Redirect] to device lo",
-        "matchCount": "2",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "58c3",
-        "name": "Flush mirred actions",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 1 dev lo",
-            "$TC actions add action mirred egress redirect index 2 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions show action mirred",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "[Mirror|Redirect] to device lo",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "d7c0",
-        "name": "Add invalid mirred direction",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "e213",
-        "name": "Add invalid mirred action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "2d89",
-        "name": "Add mirred action with invalid device",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "300b",
-        "name": "Add mirred action with duplicate index",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress redirect index 15 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "a70e",
-        "name": "Delete mirred mirror action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 5 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions del action mirred index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "3fb3",
-        "name": "Delete mirred redirect action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress redirect index 5 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions del action mirred index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "b078",
-        "name": "Add simple action",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "6d4c",
-        "name": "Add simple action with duplicate index",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Aruba\" index 4"
-        ],
-        "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "2542",
-        "name": "List simple actions",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Rock\"",
-            "$TC actions add action simple sdata \"Paper\"",
-            "$TC actions add action simple sdata \"Scissors\" index 98"
-        ],
-        "cmdUnderTest": "$TC actions list action simple",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
-        "matchCount": "3",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "ea67",
-        "name": "Delete simple action",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Blinkenlights\" index 1"
-        ],
-        "cmdUnderTest": "$TC actions delete action simple index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "8ff1",
-        "name": "Flush simple actions",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Kirk\"",
-            "$TC actions add action simple sdata \"Spock\" index 50",
-            "$TC actions add action simple sdata \"McCoy\" index 9"
-        ],
-        "cmdUnderTest": "$TC actions flush action simple",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
-        "matchCount": "0",
-        "teardown": [
-            ""
-        ]
-    },
-    {
-        "id": "6236",
-        "name": "Add skbedit action with valid mark",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 1",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "407b",
-        "name": "Add skbedit action with invalid mark",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 666777888999",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "081d",
-        "name": "Add skbedit action with priority",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit prio 99",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority :99",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "cc37",
-        "name": "Add skbedit action with invalid priority",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit prio foo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "3c95",
-        "name": "Add skbedit action with queue_mapping",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "985c",
-        "name": "Add skbedit action with invalid queue_mapping",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "224f",
-        "name": "Add skbedit action with ptype host",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype host",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "d1a3",
-        "name": "Add skbedit action with ptype otherhost",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "b9c6",
-        "name": "Add skbedit action with invalid ptype",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype openair",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype openair",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "5172",
-        "name": "List skbedit actions",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action skbedit ptype otherhost",
-            "$TC actions add action skbedit ptype broadcast",
-            "$TC actions add action skbedit mark 59",
-            "$TC actions add action skbedit mark 409"
-        ],
-        "cmdUnderTest": "$TC actions list action skbedit",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
-        "matchCount": "4",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "a6d6",
-        "name": "Add skbedit action with index",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "index 4040404040",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "38f3",
-        "name": "Delete skbedit action",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action skbedit mark 42 index 9009"
-        ],
-        "cmdUnderTest": "$TC actions del action skbedit index 9009",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 42",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "ce97",
-        "name": "Flush skbedit actions",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            "$TC actions add action skbedit mark 500",
-            "$TC actions add action skbedit mark 501",
-            "$TC actions add action skbedit mark 502",
-            "$TC actions add action skbedit mark 503",
-            "$TC actions add action skbedit mark 504",
-            "$TC actions add action skbedit mark 505",
-            "$TC actions add action skbedit mark 506"
-        ],
-        "cmdUnderTest": "$TC actions flush action skbedit",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "f02c",
-        "name": "Replace gact action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 10",
-            "$TC actions add action drop index 12"
-        ],
-        "cmdUnderTest": "$TC actions replace action ok index 12",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions ls action gact",
-        "matchPattern": "action order [0-9]*: gact action pass",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "525f",
-        "name": "Get gact action by index",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 3900800700"
-        ],
-        "cmdUnderTest": "$TC actions get action gact index 3900800700",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action gact index 3900800700",
-        "matchPattern": "index 3900800700",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "a568",
-        "name": "Add action with ife type",
-        "category": [
-            "actions",
-            "ife"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action ife",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action ife encode type 0xDEAD index 1"
-        ],
-        "cmdUnderTest": "$TC actions get action ife index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action ife index 1",
-        "matchPattern": "type 0xDEAD",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action ife"
-        ]
-    },
-    {
-        "id": "b983",
-        "name": "Add action without ife type",
-        "category": [
-            "actions",
-            "ife"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action ife",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action ife encode index 1"
-        ],
-        "cmdUnderTest": "$TC actions get action ife index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action ife index 1",
-        "matchPattern": "type 0xED3E",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action ife"
-        ]
-    }
-]
-- 
cgit v1.2.3


From cf797ac49b94df7247cf86e801ab3882d08b786d Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Fri, 13 Oct 2017 17:51:24 -0400
Subject: tc-testing: Add test cases for police and skbmod

Add basic unit tests for police and skbmod actions in tc.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/police.json        | 527 +++++++++++++++++++++
 .../tc-testing/tc-tests/actions/skbmod.json        | 372 +++++++++++++++
 2 files changed, 899 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/police.json
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
new file mode 100644
index 000000000000..0e602a3f9393
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -0,0 +1,527 @@
+[
+    {
+        "id": "49aa",
+        "name": "Add valid basic police action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 1Kbit burst 10Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "3abe",
+        "name": "Add police action with duplicate index",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 4Mbit burst 120k index 9"
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 8kbit burst 24k index 9",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x9",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "49fa",
+        "name": "Add valid police action with mtu",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 1k index 98",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 98",
+        "matchPattern": "action order [0-9]*:  police 0x62 rate 90Kbit burst 10Kb mtu 1Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "7943",
+        "name": "Add valid police action with peakrate",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 2kb peakrate 100kbit index 3",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x3 rate 90Kbit burst 10Kb mtu 2Kb peakrate 100Kbit",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "055e",
+        "name": "Add police action with peakrate and no mtu",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 5kbit burst 6kb peakrate 10kbit index 9",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x9 rate 5Kb burst 10Kb",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "f057",
+        "name": "Add police action with valid overhead",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1mbit burst 100k overhead 64 index 64",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 64",
+        "matchPattern": "action order [0-9]*:  police 0x40 rate 1Mbit burst 100Kb mtu 2Kb action reclassify overhead 64b",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "7ffb",
+        "name": "Add police action with ethernet linklayer type",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer ethernet index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions show action police",
+        "matchPattern": "action order [0-9]*:  police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "3dda",
+        "name": "Add police action with atm linklayer type",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer atm index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions show action police",
+        "matchPattern": "action order [0-9]*:  police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "551b",
+        "name": "Add police actions with conform-exceed control continue/drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed continue/drop index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action continue/drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "0c70",
+        "name": "Add police actions with conform-exceed control pass/reclassify",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/reclassify index 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x4 rate 3Mbit burst 250Kb mtu 2Kb action pass/reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "d946",
+        "name": "Add police actions with conform-exceed control pass/pipe",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/pipe index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x5 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "336e",
+        "name": "Delete police action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 5mbit burst 2m index 12"
+        ],
+        "cmdUnderTest": "$TC actions delete action police index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0xc rate 5Mb burst 2Mb",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "77fa",
+        "name": "Get single police action from many actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions get action police index 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 4",
+        "matchPattern": "action order [0-9]*:  police 0x4 rate 4Mbit burst 400Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "aa43",
+        "name": "Get single police action without specifying index",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action police",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action police",
+        "matchPattern": "action order [0-9]*:  police",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "858b",
+        "name": "List police actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions list action police",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x[1-8] rate [1-8]Mbit burst [1-8]00Kb",
+        "matchCount": "8",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "1c3a",
+        "name": "Flush police actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions flush action police",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police",
+        "matchCount": "0",
+        "teardown": [
+            ""
+        ]
+    },
+    {
+        "id": "7326",
+        "name": "Add police action with control continue",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "34fa",
+        "name": "Add police action with control drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "8dd5",
+        "name": "Add police action with control ok",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "b9d1",
+        "name": "Add police action with control reclassify",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "c534",
+        "name": "Add police action with control pipe",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
new file mode 100644
index 000000000000..e34075059c26
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -0,0 +1,372 @@
+[
+    {
+        "id": "7d50",
+        "name": "Add skbmod action to set destination mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set dmac 11:22:33:44:55:66 index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set dmac 11:22:33:44:55:66\\s+index 5",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "9b29",
+        "name": "Add skbmod action to set source mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 77:88:99:AA:BB:CC index 7",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 7",
+        "matchPattern": "action order [0-9]*: skbmod pipe set smac 77:88:99:aa:bb:cc\\s+index 7",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "1724",
+        "name": "Add skbmod action with invalid mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 00:44:55:44:55",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set smac 00:44:55:44:55",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "3cf1",
+        "name": "Add skbmod action with valid etype",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFE",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "a749",
+        "name": "Add skbmod action with invalid etype",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefef",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFEF",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "bfe6",
+        "name": "Add skbmod action to swap mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod swap mac",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 1",
+        "matchPattern": "action order [0-9]*: skbmod pipe swap mac",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "839b",
+        "name": "Add skbmod action with control pipe",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod swap mac pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe swap mac",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "c167",
+        "name": "Add skbmod action with control reclassify",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xbeef reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod reclassify set etype 0xBEEF",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "0c2f",
+        "name": "Add skbmod action with control drop",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0x0001 drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 1",
+        "matchPattern": "action order [0-9]*: skbmod drop set etype 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "d113",
+        "name": "Add skbmod action with control continue",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0x1 continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod continue set etype 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "7242",
+        "name": "Add skbmod action with control pass",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 00:00:00:00:00:01 pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pass set smac 00:00:00:00:00:01",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "58cb",
+        "name": "List skbmod actions",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions ls action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod",
+        "matchCount": "5",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "9aa8",
+        "name": "Get a single skbmod action from a list",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions ls action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 4",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "e93a",
+        "name": "Delete an skbmod action",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x1111 index 909"
+        ],
+        "cmdUnderTest": "$TC actions del action skbmod index 909",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x1111\\s+index 909",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "40c2",
+        "name": "Flush skbmod actions",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions flush action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    }
+]
-- 
cgit v1.2.3


From 7f6661a78a50c3bae8c9f71f67487abbea64dbb3 Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Fri, 13 Oct 2017 17:51:25 -0400
Subject: tc-testing: fix the -l argument bug in tdc.py

This patch fixes a bug in the tdc script, where executing tdc
with the -l argument would cause the tests to start running
as opposed to listing all the known test cases.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index cd61b7844c0d..d2391df2cf7d 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -49,7 +49,7 @@ def exec_cmd(command, nsonly=True):
         stderr=subprocess.PIPE)
     (rawout, serr) = proc.communicate()
 
-    if proc.returncode != 0:
+    if proc.returncode != 0 and len(serr) > 0:
         foutput = serr.decode("utf-8")
     else:
         foutput = rawout.decode("utf-8")
@@ -203,7 +203,7 @@ def set_args(parser):
                         help='Run tests only from the specified category, or if no category is specified, list known categories.')
     parser.add_argument('-f', '--file', type=str,
                         help='Run tests from the specified file')
-    parser.add_argument('-l', '--list', type=str, nargs='?', const="", metavar='CATEGORY',
+    parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY',
                         help='List all test cases, or those only within the specified category')
     parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID',
                         help='Display the test case with specified id')
@@ -357,10 +357,10 @@ def set_operation_mode(args):
     testcases = get_categorized_testlist(alltests, ucat)
 
     if args.list:
-        if (len(args.list) == 0):
+        if (args.list == "++"):
             list_test_cases(alltests)
             exit(0)
-        elif(len(args.list > 0)):
+        elif(len(args.list) > 0):
             if (args.list not in ucat):
                 print("Unknown category " + args.list)
                 print("Available categories:")
-- 
cgit v1.2.3


From ec04aa3ae87b895dbc674a7e0b78b670f73a2c22 Mon Sep 17 00:00:00 2001
From: Markus Mayer <mmayer@broadcom.com>
Date: Wed, 27 Sep 2017 16:02:35 -0700
Subject: tools/thermal: tmon: use "-fstack-protector" only if supported

Most, but not all, toolchains support the "-fstack-protector" flag. We
check if the compiler supports the flag before using it. This allows
tmon to be compiled for more environments.

Signed-off-by: Markus Mayer <mmayer@broadcom.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 tools/thermal/tmon/Makefile | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 3a961e998281..5777bc78173f 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -1,8 +1,13 @@
+# We need this for the "cc-option" macro.
+include ../../../scripts/Kbuild.include
+
 VERSION = 1.0
 
 BINDIR=usr/bin
 WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int
-CFLAGS+= -O1 ${WARNFLAGS} -fstack-protector
+CFLAGS+= -O1 ${WARNFLAGS}
+# Add "-fstack-protector" only if toolchain supports it.
+CFLAGS+= $(call cc-option,-fstack-protector)
 CC=$(CROSS_COMPILE)gcc
 
 CFLAGS+=-D VERSION=\"$(VERSION)\"
-- 
cgit v1.2.3


From c21568ffabed918882c61eada79146706bd94684 Mon Sep 17 00:00:00 2001
From: Markus Mayer <mmayer@broadcom.com>
Date: Wed, 27 Sep 2017 16:02:36 -0700
Subject: tools/thermal: tmon: allow $(CC) to be defined externally

It can be helpful, especially when using a build system, to set the C
compiler externally.

Signed-off-by: Markus Mayer <mmayer@broadcom.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 tools/thermal/tmon/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 5777bc78173f..581da716ea1c 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -8,7 +8,7 @@ WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-
 CFLAGS+= -O1 ${WARNFLAGS}
 # Add "-fstack-protector" only if toolchain supports it.
 CFLAGS+= $(call cc-option,-fstack-protector)
-CC=$(CROSS_COMPILE)gcc
+CC?= $(CROSS_COMPILE)gcc
 
 CFLAGS+=-D VERSION=\"$(VERSION)\"
 LDFLAGS+=
-- 
cgit v1.2.3


From 501a5c71d1f754e44142af6cae59042a8c3b2a11 Mon Sep 17 00:00:00 2001
From: Markus Mayer <mmayer@broadcom.com>
Date: Wed, 27 Sep 2017 16:02:37 -0700
Subject: tools/thermal: tmon: use $(PKG_CONFIG) instead of hard-coding
 pkg-config

To ease cross-compiling, make use of the $(PKG_CONFIG) variable rather
than hard-coding calls to pkg-config.

Signed-off-by: Markus Mayer <mmayer@broadcom.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 tools/thermal/tmon/Makefile | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 581da716ea1c..1e11bd38a6b4 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -9,6 +9,7 @@ CFLAGS+= -O1 ${WARNFLAGS}
 # Add "-fstack-protector" only if toolchain supports it.
 CFLAGS+= $(call cc-option,-fstack-protector)
 CC?= $(CROSS_COMPILE)gcc
+PKG_CONFIG?= pkg-config
 
 CFLAGS+=-D VERSION=\"$(VERSION)\"
 LDFLAGS+=
@@ -23,12 +24,12 @@ STATIC := --static
 endif
 
 TMON_LIBS=-lm -lpthread
-TMON_LIBS += $(shell pkg-config --libs $(STATIC) panelw ncursesw 2> /dev/null || \
-		     pkg-config --libs $(STATIC) panel ncurses 2> /dev/null || \
+TMON_LIBS += $(shell $(PKG_CONFIG) --libs $(STATIC) panelw ncursesw 2> /dev/null || \
+		     $(PKG_CONFIG) --libs $(STATIC) panel ncurses 2> /dev/null || \
 		     echo -lpanel -lncurses)
 
-CFLAGS    += $(shell pkg-config --cflags $(STATIC) panelw ncursesw 2> /dev/null || \
-		     pkg-config --cflags $(STATIC) panel ncurses 2> /dev/null)
+CFLAGS    += $(shell $(PKG_CONFIG) --cflags $(STATIC) panelw ncursesw 2> /dev/null || \
+		     $(PKG_CONFIG) --cflags $(STATIC) panel ncurses 2> /dev/null)
 
 OBJS = tmon.o tui.o sysfs.o pid.o
 OBJS +=
-- 
cgit v1.2.3


From 6710e1126934d8b4372b4d2f9ae1646cd3f151bf Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 16 Oct 2017 12:19:28 +0200
Subject: bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP

The 'cpumap' is primarily used as a backend map for XDP BPF helper
call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.

This patch implement the main part of the map.  It is not connected to
the XDP redirect system yet, and no SKB allocation are done yet.

The main concern in this patch is to ensure the datapath can run
without any locking.  This adds complexity to the setup and tear-down
procedure, which assumptions are extra carefully documented in the
code comments.

V2:
 - make sure array isn't larger than NR_CPUS
 - make sure CPUs added is a valid possible CPU

V3: fix nitpicks from Jakub Kicinski <kubakici@wp.pl>

V5:
 - Restrict map allocation to root / CAP_SYS_ADMIN
 - WARN_ON_ONCE if queue is not empty on tear-down
 - Return -EPERM on memlock limit instead of -ENOMEM
 - Error code in __cpu_map_entry_alloc() also handle ptr_ring_cleanup()
 - Moved cpu_map_enqueue() to next patch

V6: all notice by Daniel Borkmann
 - Fix err return code in cpu_map_alloc() introduced in V5
 - Move cpu_possible() check after max_entries boundary check
 - Forbid usage initially in check_map_func_compatibility()

V7:
 - Fix alloc error path spotted by Daniel Borkmann
 - Did stress test adding+removing CPUs from the map concurrently
 - Fixed refcnt issue on cpu_map_entry, kthread started too soon
 - Make sure packets are flushed during tear-down, involved use of
   rcu_barrier() and kthread_run only exit after queue is empty
 - Fix alloc error path in __cpu_map_entry_alloc() for ptr_ring

V8:
 - Nitpicking comments and gramma by Edward Cree
 - Fix missing semi-colon introduced in V7 due to rebasing
 - Move struct bpf_cpu_map_entry members cpu+map_id to tracepoint patch

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf_types.h      |   1 +
 include/uapi/linux/bpf.h       |   1 +
 kernel/bpf/Makefile            |   1 +
 kernel/bpf/cpumap.c            | 560 +++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           |   8 +-
 kernel/bpf/verifier.c          |   5 +
 tools/include/uapi/linux/bpf.h |   1 +
 7 files changed, 576 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/cpumap.c

(limited to 'tools')

diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 6f1a567667b8..814c1081a4a9 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
 #ifdef CONFIG_STREAM_PARSER
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 #endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6db9e1d679cd..4303fb6c3817 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_HASH_OF_MAPS,
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
+	BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 53fb09f92e3f..e597daae6120 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
 ifeq ($(CONFIG_STREAM_PARSER),y)
 obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
 endif
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
new file mode 100644
index 000000000000..e1e25ddba038
--- /dev/null
+++ b/kernel/bpf/cpumap.c
@@ -0,0 +1,560 @@
+/* bpf/cpumap.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2.  See COPYING.
+ */
+
+/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
+ * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
+ *
+ * Unlike devmap which redirects XDP frames out another NIC device,
+ * this map type redirects raw XDP frames to another CPU.  The remote
+ * CPU will do SKB-allocation and call the normal network stack.
+ *
+ * This is a scalability and isolation mechanism, that allow
+ * separating the early driver network XDP layer, from the rest of the
+ * netstack, and assigning dedicated CPUs for this stage.  This
+ * basically allows for 10G wirespeed pre-filtering via bpf.
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/capability.h>
+
+/* General idea: XDP packets getting XDP redirected to another CPU,
+ * will maximum be stored/queued for one driver ->poll() call.  It is
+ * guaranteed that setting flush bit and flush operation happen on
+ * same CPU.  Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
+ * which queue in bpf_cpu_map_entry contains packets.
+ */
+
+#define CPU_MAP_BULK_SIZE 8  /* 8 == one cacheline on 64-bit archs */
+struct xdp_bulk_queue {
+	void *q[CPU_MAP_BULK_SIZE];
+	unsigned int count;
+};
+
+/* Struct for every remote "destination" CPU in map */
+struct bpf_cpu_map_entry {
+	u32 qsize;  /* Queue size placeholder for map lookup */
+
+	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
+	struct xdp_bulk_queue __percpu *bulkq;
+
+	/* Queue with potential multi-producers, and single-consumer kthread */
+	struct ptr_ring *queue;
+	struct task_struct *kthread;
+	struct work_struct kthread_stop_wq;
+
+	atomic_t refcnt; /* Control when this struct can be free'ed */
+	struct rcu_head rcu;
+};
+
+struct bpf_cpu_map {
+	struct bpf_map map;
+	/* Below members specific for map type */
+	struct bpf_cpu_map_entry **cpu_map;
+	unsigned long __percpu *flush_needed;
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+			     struct xdp_bulk_queue *bq);
+
+static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
+{
+	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_cpu_map *cmap;
+	int err = -ENOMEM;
+	u64 cost;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+		return ERR_PTR(-EINVAL);
+
+	cmap = kzalloc(sizeof(*cmap), GFP_USER);
+	if (!cmap)
+		return ERR_PTR(-ENOMEM);
+
+	/* mandatory map attributes */
+	cmap->map.map_type = attr->map_type;
+	cmap->map.key_size = attr->key_size;
+	cmap->map.value_size = attr->value_size;
+	cmap->map.max_entries = attr->max_entries;
+	cmap->map.map_flags = attr->map_flags;
+	cmap->map.numa_node = bpf_map_attr_numa_node(attr);
+
+	/* Pre-limit array size based on NR_CPUS, not final CPU check */
+	if (cmap->map.max_entries > NR_CPUS) {
+		err = -E2BIG;
+		goto free_cmap;
+	}
+
+	/* make sure page count doesn't overflow */
+	cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
+	cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_cmap;
+	cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* Notice returns -EPERM on if map size is larger than memlock limit */
+	ret = bpf_map_precharge_memlock(cmap->map.pages);
+	if (ret) {
+		err = ret;
+		goto free_cmap;
+	}
+
+	/* A per cpu bitfield with a bit per possible CPU in map  */
+	cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
+					    __alignof__(unsigned long));
+	if (!cmap->flush_needed)
+		goto free_cmap;
+
+	/* Alloc array for possible remote "destination" CPUs */
+	cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
+					   sizeof(struct bpf_cpu_map_entry *),
+					   cmap->map.numa_node);
+	if (!cmap->cpu_map)
+		goto free_percpu;
+
+	return &cmap->map;
+free_percpu:
+	free_percpu(cmap->flush_needed);
+free_cmap:
+	kfree(cmap);
+	return ERR_PTR(err);
+}
+
+void __cpu_map_queue_destructor(void *ptr)
+{
+	/* The tear-down procedure should have made sure that queue is
+	 * empty.  See __cpu_map_entry_replace() and work-queue
+	 * invoked cpu_map_kthread_stop(). Catch any broken behaviour
+	 * gracefully and warn once.
+	 */
+	if (WARN_ON_ONCE(ptr))
+		page_frag_free(ptr);
+}
+
+static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+	if (atomic_dec_and_test(&rcpu->refcnt)) {
+		/* The queue should be empty at this point */
+		ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor);
+		kfree(rcpu->queue);
+		kfree(rcpu);
+	}
+}
+
+static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+	atomic_inc(&rcpu->refcnt);
+}
+
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+	struct bpf_cpu_map_entry *rcpu;
+
+	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+	 * as it waits until all in-flight call_rcu() callbacks complete.
+	 */
+	rcu_barrier();
+
+	/* kthread_stop will wake_up_process and wait for it to complete */
+	kthread_stop(rcpu->kthread);
+}
+
+static int cpu_map_kthread_run(void *data)
+{
+	struct bpf_cpu_map_entry *rcpu = data;
+
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	/* When kthread gives stop order, then rcpu have been disconnected
+	 * from map, thus no new packets can enter. Remaining in-flight
+	 * per CPU stored packets are flushed to this queue.  Wait honoring
+	 * kthread_stop signal until queue is empty.
+	 */
+	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		struct xdp_pkt *xdp_pkt;
+
+		schedule();
+		/* Do work */
+		while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) {
+			/* For now just "refcnt-free" */
+			page_frag_free(xdp_pkt);
+		}
+		__set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+
+	put_cpu_map_entry(rcpu);
+	return 0;
+}
+
+struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
+{
+	gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+	struct bpf_cpu_map_entry *rcpu;
+	int numa, err;
+
+	/* Have map->numa_node, but choose node of redirect target CPU */
+	numa = cpu_to_node(cpu);
+
+	rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+	if (!rcpu)
+		return NULL;
+
+	/* Alloc percpu bulkq */
+	rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
+					 sizeof(void *), gfp);
+	if (!rcpu->bulkq)
+		goto free_rcu;
+
+	/* Alloc queue */
+	rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+	if (!rcpu->queue)
+		goto free_bulkq;
+
+	err = ptr_ring_init(rcpu->queue, qsize, gfp);
+	if (err)
+		goto free_queue;
+
+	rcpu->qsize = qsize;
+
+	/* Setup kthread */
+	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
+					       "cpumap/%d/map:%d", cpu, map_id);
+	if (IS_ERR(rcpu->kthread))
+		goto free_ptr_ring;
+
+	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
+	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
+
+	/* Make sure kthread runs on a single CPU */
+	kthread_bind(rcpu->kthread, cpu);
+	wake_up_process(rcpu->kthread);
+
+	return rcpu;
+
+free_ptr_ring:
+	ptr_ring_cleanup(rcpu->queue, NULL);
+free_queue:
+	kfree(rcpu->queue);
+free_bulkq:
+	free_percpu(rcpu->bulkq);
+free_rcu:
+	kfree(rcpu);
+	return NULL;
+}
+
+void __cpu_map_entry_free(struct rcu_head *rcu)
+{
+	struct bpf_cpu_map_entry *rcpu;
+	int cpu;
+
+	/* This cpu_map_entry have been disconnected from map and one
+	 * RCU graze-period have elapsed.  Thus, XDP cannot queue any
+	 * new packets and cannot change/set flush_needed that can
+	 * find this entry.
+	 */
+	rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+
+	/* Flush remaining packets in percpu bulkq */
+	for_each_online_cpu(cpu) {
+		struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
+
+		/* No concurrent bq_enqueue can run at this point */
+		bq_flush_to_queue(rcpu, bq);
+	}
+	free_percpu(rcpu->bulkq);
+	/* Cannot kthread_stop() here, last put free rcpu resources */
+	put_cpu_map_entry(rcpu);
+}
+
+/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
+ * ensure any driver rcu critical sections have completed, but this
+ * does not guarantee a flush has happened yet. Because driver side
+ * rcu_read_lock/unlock only protects the running XDP program.  The
+ * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
+ * pending flush op doesn't fail.
+ *
+ * The bpf_cpu_map_entry is still used by the kthread, and there can
+ * still be pending packets (in queue and percpu bulkq).  A refcnt
+ * makes sure to last user (kthread_stop vs. call_rcu) free memory
+ * resources.
+ *
+ * The rcu callback __cpu_map_entry_free flush remaining packets in
+ * percpu bulkq to queue.  Due to caller map_delete_elem() disable
+ * preemption, cannot call kthread_stop() to make sure queue is empty.
+ * Instead a work_queue is started for stopping kthread,
+ * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * stopping kthread, emptying the queue.
+ */
+void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+			     u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+{
+	struct bpf_cpu_map_entry *old_rcpu;
+
+	old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+	if (old_rcpu) {
+		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
+		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
+		schedule_work(&old_rcpu->kthread_stop_wq);
+	}
+}
+
+int cpu_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	u32 key_cpu = *(u32 *)key;
+
+	if (key_cpu >= map->max_entries)
+		return -EINVAL;
+
+	/* notice caller map_delete_elem() use preempt_disable() */
+	__cpu_map_entry_replace(cmap, key_cpu, NULL);
+	return 0;
+}
+
+int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
+				u64 map_flags)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpu_map_entry *rcpu;
+
+	/* Array index key correspond to CPU number */
+	u32 key_cpu = *(u32 *)key;
+	/* Value is the queue size */
+	u32 qsize = *(u32 *)value;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(key_cpu >= cmap->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+	if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+		return -EOVERFLOW;
+
+	/* Make sure CPU is a valid possible cpu */
+	if (!cpu_possible(key_cpu))
+		return -ENODEV;
+
+	if (qsize == 0) {
+		rcpu = NULL; /* Same as deleting */
+	} else {
+		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
+		rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+		if (!rcpu)
+			return -ENOMEM;
+	}
+	rcu_read_lock();
+	__cpu_map_entry_replace(cmap, key_cpu, rcpu);
+	rcu_read_unlock();
+	return 0;
+}
+
+void cpu_map_free(struct bpf_map *map)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	int cpu;
+	u32 i;
+
+	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the bpf programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete. The rcu critical section only guarantees
+	 * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
+	 * It does __not__ ensure pending flush operations (if any) are
+	 * complete.
+	 */
+	synchronize_rcu();
+
+	/* To ensure all pending flush operations have completed wait for flush
+	 * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+	 * Because the above synchronize_rcu() ensures the map is disconnected
+	 * from the program we can assume no new bits will be set.
+	 */
+	for_each_online_cpu(cpu) {
+		unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu);
+
+		while (!bitmap_empty(bitmap, cmap->map.max_entries))
+			cond_resched();
+	}
+
+	/* For cpu_map the remote CPUs can still be using the entries
+	 * (struct bpf_cpu_map_entry).
+	 */
+	for (i = 0; i < cmap->map.max_entries; i++) {
+		struct bpf_cpu_map_entry *rcpu;
+
+		rcpu = READ_ONCE(cmap->cpu_map[i]);
+		if (!rcpu)
+			continue;
+
+		/* bq flush and cleanup happens after RCU graze-period */
+		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+	}
+	free_percpu(cmap->flush_needed);
+	bpf_map_area_free(cmap->cpu_map);
+	kfree(cmap);
+}
+
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpu_map_entry *rcpu;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	rcpu = READ_ONCE(cmap->cpu_map[key]);
+	return rcpu;
+}
+
+static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_cpu_map_entry *rcpu =
+		__cpu_map_lookup_elem(map, *(u32 *)key);
+
+	return rcpu ? &rcpu->qsize : NULL;
+}
+
+static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= cmap->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == cmap->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+const struct bpf_map_ops cpu_map_ops = {
+	.map_alloc		= cpu_map_alloc,
+	.map_free		= cpu_map_free,
+	.map_delete_elem	= cpu_map_delete_elem,
+	.map_update_elem	= cpu_map_update_elem,
+	.map_lookup_elem	= cpu_map_lookup_elem,
+	.map_get_next_key	= cpu_map_get_next_key,
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+			     struct xdp_bulk_queue *bq)
+{
+	struct ptr_ring *q;
+	int i;
+
+	if (unlikely(!bq->count))
+		return 0;
+
+	q = rcpu->queue;
+	spin_lock(&q->producer_lock);
+
+	for (i = 0; i < bq->count; i++) {
+		void *xdp_pkt = bq->q[i];
+		int err;
+
+		err = __ptr_ring_produce(q, xdp_pkt);
+		if (err) {
+			/* Free xdp_pkt */
+			page_frag_free(xdp_pkt);
+		}
+	}
+	bq->count = 0;
+	spin_unlock(&q->producer_lock);
+
+	return 0;
+}
+
+/* Notice: Will change in later patch */
+struct xdp_pkt {
+	void *data;
+	u16 len;
+	u16 headroom;
+};
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
+{
+	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+
+	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
+		bq_flush_to_queue(rcpu, bq);
+
+	/* Notice, xdp_buff/page MUST be queued here, long enough for
+	 * driver to code invoking us to finished, due to driver
+	 * (e.g. ixgbe) recycle tricks based on page-refcnt.
+	 *
+	 * Thus, incoming xdp_pkt is always queued here (else we race
+	 * with another CPU on page-refcnt and remaining driver code).
+	 * Queue time is very short, as driver will invoke flush
+	 * operation, when completing napi->poll call.
+	 */
+	bq->q[bq->count++] = xdp_pkt;
+	return 0;
+}
+
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+
+	__set_bit(bit, bitmap);
+}
+
+void __cpu_map_flush(struct bpf_map *map)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+	u32 bit;
+
+	/* The napi->poll softirq makes sure __cpu_map_insert_ctx()
+	 * and __cpu_map_flush() happen on same CPU. Thus, the percpu
+	 * bitmap indicate which percpu bulkq have packets.
+	 */
+	for_each_set_bit(bit, bitmap, map->max_entries) {
+		struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]);
+		struct xdp_bulk_queue *bq;
+
+		/* This is possible if entry is removed by user space
+		 * between xdp redirect and flush op.
+		 */
+		if (unlikely(!rcpu))
+			continue;
+
+		__clear_bit(bit, bitmap);
+
+		/* Flush all frames in bulkq to real queue */
+		bq = this_cpu_ptr(rcpu->bulkq);
+		bq_flush_to_queue(rcpu, bq);
+
+		/* If already running, costs spin_lock_irqsave + smb_mb */
+		wake_up_process(rcpu->kthread);
+	}
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d124e702e040..54fba06942f5 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -592,6 +592,12 @@ static int map_update_elem(union bpf_attr *attr)
 	if (copy_from_user(value, uvalue, value_size) != 0)
 		goto free_value;
 
+	/* Need to create a kthread, thus must support schedule */
+	if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+		err = map->ops->map_update_elem(map, key, value, attr->flags);
+		goto out;
+	}
+
 	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
 	 * inside bpf map update or delete otherwise deadlocks are possible
 	 */
@@ -622,7 +628,7 @@ static int map_update_elem(union bpf_attr *attr)
 	}
 	__this_cpu_dec(bpf_prog_active);
 	preempt_enable();
-
+out:
 	if (!err)
 		trace_bpf_map_update_elem(map, ufd, key, value);
 free_value:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9755279d94cb..cefa64be9a2f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1444,6 +1444,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_redirect_map)
 			goto error;
 		break;
+	/* Restrict bpf side of cpumap, open when use-cases appear */
+	case BPF_MAP_TYPE_CPUMAP:
+		if (func_id != BPF_FUNC_redirect_map)
+			goto error;
+		break;
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 		if (func_id != BPF_FUNC_map_lookup_elem)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index fb4fb81ce5b0..fa93033dc521 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_HASH_OF_MAPS,
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
+	BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
-- 
cgit v1.2.3


From 2dc7c1fef9565c73c5054fd3c134afada09476c1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 16 Oct 2017 10:12:54 -0700
Subject: tools: bpftool: use more common tag format

Program tag is usually displayed as string of bytes without
any separators (e.g. as "aa5520b1090cfeb6" vs MAC addr-like
format bpftool uses currently: "aa:55:20:b1:09:0c:fe:b6").
Make bptfool use the more common format both for displaying
the tag and selecting the program by tag.

This was pointed out in review but I misunderstood the comment.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 2 +-
 tools/bpf/bpftool/main.h                         | 3 +--
 tools/bpf/bpftool/prog.c                         | 2 +-
 3 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 04d12f768f06..3968f0bd37db 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -55,7 +55,7 @@ EXAMPLES
 **# bpftool prog show**
 ::
 
-  10: xdp  name some_prog  tag 00:5a:3d:21:23:62:0c:8b
+  10: xdp  name some_prog  tag 005a3d2123620c8b
 	loaded_at Sep 29/20:11  uid 0
 	xlated 528B  jited 370B  memlock 4096B  map_ids 10
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 8e809b2bb311..844e4ef6db56 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -53,8 +53,7 @@
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
 #define BAD_ARG()	({ err("what is '%s'?\n", *argv); -1; })
 
-#define BPF_TAG_FMT	"%02hhx:%02hhx:%02hhx:%02hhx:"	\
-			"%02hhx:%02hhx:%02hhx:%02hhx"
+#define BPF_TAG_FMT	"%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
 
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 9e2681c83717..d60f5307b6e2 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -224,7 +224,7 @@ static int show_prog(int fd)
 		printf("name %s  ", info.name);
 
 	printf("tag ");
-	print_hex(info.tag, BPF_TAG_SIZE, ":");
+	print_hex(info.tag, BPF_TAG_SIZE, "");
 	printf("\n");
 
 	if (info.load_time) {
-- 
cgit v1.2.3


From e043325b308745d6968673e7b53080bd7cc39f08 Mon Sep 17 00:00:00 2001
From: Chenbo Feng <fengc@google.com>
Date: Wed, 18 Oct 2017 13:00:23 -0700
Subject: bpf: Add tests for eBPF file mode

Two related tests are added into bpf selftest to test read only map and
write only map. The tests verified the read only and write only flags
are working on hash maps.

Signed-off-by: Chenbo Feng <fengc@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_maps.c | 48 +++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index fe3a443a1102..896f23cfe918 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1033,6 +1033,51 @@ static void test_map_parallel(void)
 	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 }
 
+static void test_map_rdonly(void)
+{
+	int i, fd, key = 0, value = 0;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+			    MAP_SIZE, map_flags | BPF_F_RDONLY);
+	if (fd < 0) {
+		printf("Failed to create map for read only test '%s'!\n",
+		       strerror(errno));
+		exit(1);
+	}
+
+	key = 1;
+	value = 1234;
+	/* Insert key=1 element. */
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 &&
+	       errno == EPERM);
+
+	/* Check that key=2 is not found. */
+	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
+	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT);
+}
+
+static void test_map_wronly(void)
+{
+	int i, fd, key = 0, value = 0;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+			    MAP_SIZE, map_flags | BPF_F_WRONLY);
+	if (fd < 0) {
+		printf("Failed to create map for read only test '%s'!\n",
+		       strerror(errno));
+		exit(1);
+	}
+
+	key = 1;
+	value = 1234;
+	/* Insert key=1 element. */
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0)
+
+	/* Check that key=2 is not found. */
+	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
+	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
+}
+
 static void run_all_tests(void)
 {
 	test_hashmap(0, NULL);
@@ -1050,6 +1095,9 @@ static void run_all_tests(void)
 	test_map_large();
 	test_map_parallel();
 	test_map_stress();
+
+	test_map_rdonly();
+	test_map_wronly();
 }
 
 int main(void)
-- 
cgit v1.2.3


From 9cbe1f581d17baff7e93936feb041c90b29eb6a8 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:19 -0700
Subject: tools: bpftool: add pointer to file argument to print_hex()

Make print_hex() able to print to any file instead of standard output
only, and rename it to fprint_hex(). The function can now be called with
the info() macro, for example, without splitting the output between
standard and error outputs.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/main.c |  8 ++++----
 tools/bpf/bpftool/main.h |  2 +-
 tools/bpf/bpftool/map.c  | 20 ++++++++++----------
 tools/bpf/bpftool/prog.c |  4 ++--
 4 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index e02d00d6e00b..8662199ee050 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -100,7 +100,7 @@ bool is_prefix(const char *pfx, const char *str)
 	return !memcmp(str, pfx, strlen(pfx));
 }
 
-void print_hex(void *arg, unsigned int n, const char *sep)
+void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep)
 {
 	unsigned char *data = arg;
 	unsigned int i;
@@ -111,13 +111,13 @@ void print_hex(void *arg, unsigned int n, const char *sep)
 		if (!i)
 			/* nothing */;
 		else if (!(i % 16))
-			printf("\n");
+			fprintf(f, "\n");
 		else if (!(i % 8))
-			printf("  ");
+			fprintf(f, "  ");
 		else
 			pfx = sep;
 
-		printf("%s%02hhx", i ? pfx : "", data[i]);
+		fprintf(f, "%s%02hhx", i ? pfx : "", data[i]);
 	}
 }
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 844e4ef6db56..41e6c7d3fcad 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -67,7 +67,7 @@ enum bpf_obj_type {
 extern const char *bin_name;
 
 bool is_prefix(const char *pfx, const char *str);
-void print_hex(void *arg, unsigned int n, const char *sep);
+void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __attribute__((noreturn));
 
 struct cmd {
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 0528a5379e6c..b1dad76215ed 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -216,12 +216,12 @@ static void print_entry(struct bpf_map_info *info, unsigned char *key,
 			!break_names;
 
 		printf("key:%c", break_names ? '\n' : ' ');
-		print_hex(key, info->key_size, " ");
+		fprint_hex(stdout, key, info->key_size, " ");
 
 		printf(single_line ? "  " : "\n");
 
 		printf("value:%c", break_names ? '\n' : ' ');
-		print_hex(value, info->value_size, " ");
+		fprint_hex(stdout, value, info->value_size, " ");
 
 		printf("\n");
 	} else {
@@ -230,13 +230,13 @@ static void print_entry(struct bpf_map_info *info, unsigned char *key,
 		n = get_possible_cpus();
 
 		printf("key:\n");
-		print_hex(key, info->key_size, " ");
+		fprint_hex(stdout, key, info->key_size, " ");
 		printf("\n");
 		for (i = 0; i < n; i++) {
 			printf("value (CPU %02d):%c",
 			       i, info->value_size > 16 ? '\n' : ' ');
-			print_hex(value + i * info->value_size,
-				  info->value_size, " ");
+			fprint_hex(stdout, value + i * info->value_size,
+				   info->value_size, " ");
 			printf("\n");
 		}
 	}
@@ -492,8 +492,8 @@ static int do_dump(int argc, char **argv)
 			print_entry(&info, key, value);
 		} else {
 			info("can't lookup element with key: ");
-			print_hex(key, info.key_size, " ");
-			printf("\n");
+			fprint_hex(stderr, key, info.key_size, " ");
+			fprintf(stderr, "\n");
 		}
 
 		prev_key = key;
@@ -587,7 +587,7 @@ static int do_lookup(int argc, char **argv)
 		print_entry(&info, key, value);
 	} else if (errno == ENOENT) {
 		printf("key:\n");
-		print_hex(key, info.key_size, " ");
+		fprint_hex(stdout, key, info.key_size, " ");
 		printf("\n\nNot found\n");
 	} else {
 		err("lookup failed: %s\n", strerror(errno));
@@ -642,14 +642,14 @@ static int do_getnext(int argc, char **argv)
 
 	if (key) {
 		printf("key:\n");
-		print_hex(key, info.key_size, " ");
+		fprint_hex(stdout, key, info.key_size, " ");
 		printf("\n");
 	} else {
 		printf("key: None\n");
 	}
 
 	printf("next key:\n");
-	print_hex(nextkey, info.key_size, " ");
+	fprint_hex(stdout, nextkey, info.key_size, " ");
 	printf("\n");
 
 exit_free:
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d60f5307b6e2..aa6d72ea3807 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -224,7 +224,7 @@ static int show_prog(int fd)
 		printf("name %s  ", info.name);
 
 	printf("tag ");
-	print_hex(info.tag, BPF_TAG_SIZE, "");
+	fprint_hex(stdout, info.tag, BPF_TAG_SIZE, "");
 	printf("\n");
 
 	if (info.load_time) {
@@ -319,7 +319,7 @@ static void dump_xlated(void *buf, unsigned int len, bool opcodes)
 
 		if (opcodes) {
 			printf("       ");
-			print_hex(insn + i, 8, " ");
+			fprint_hex(stdout, insn + i, 8, " ");
 			printf("\n");
 		}
 
-- 
cgit v1.2.3


From 1739c26da72c4170c86c368c75133adbb740efef Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:20 -0700
Subject: tools: bpftool: fix return value when all eBPF programs have been
 shown

Change the program to have a more consistent return code. Specifically,
do not make bpftool return an error code simply because it reaches the
end of the list of the eBPF programs to show.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/prog.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index aa6d72ea3807..ede7957adcd9 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -275,8 +275,10 @@ static int do_show(int argc, char **argv)
 	while (true) {
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
-			if (errno == ENOENT)
+			if (errno == ENOENT) {
+				err = 0;
 				break;
+			}
 			err("can't get next program: %s\n", strerror(errno));
 			if (errno == EINVAL)
 				err("kernel too old?\n");
-- 
cgit v1.2.3


From 1d84487e2a2b98892c3dec7934604e9b76577aa6 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:21 -0700
Subject: tools: bpftool: use err() instead of info() if there are too many
 insns

Make error messages and return codes more consistent. Specifically,
replace the use of info() macro with err() when too many eBPF
instructions are received to be dumped, given that bpftool returns with
a non-null exit value in that case.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/prog.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index ede7957adcd9..6c03d2ea3f79 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -416,7 +416,7 @@ static int do_dump(int argc, char **argv)
 	}
 
 	if (*member_len > buf_size) {
-		info("too many instructions returned\n");
+		err("too many instructions returned\n");
 		goto err_free;
 	}
 
-- 
cgit v1.2.3


From 9f606179c84930ada1e347b6d84bb913c8492fec Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:22 -0700
Subject: tools: bpftool: add `bpftool prog help` as real command i.r.t exit
 code

Make error messages and return codes more consistent. Specifically, make
`bpftool prog help` a real command, instead of printing usage by default
for a non-recognized "help" command. Output is the same, but this makes
bpftool return with a success value instead of an error.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/prog.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 6c03d2ea3f79..355c14325622 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -475,6 +475,7 @@ static int do_help(int argc, char **argv)
 
 static const struct cmd cmds[] = {
 	{ "show",	do_show },
+	{ "help",	do_help },
 	{ "dump",	do_dump },
 	{ "pin",	do_pin },
 	{ 0 }
-- 
cgit v1.2.3


From d9c0b48db9f4b870535b6d7255638347e770633f Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:23 -0700
Subject: tools: bpftool: print only one error message on byte parsing failure

Make error messages more consistent. Specifically, when bpftool fails at
parsing map key bytes, make it print a single error message to stderr
and return from the function, instead of (always) printing a second
error message afterwards.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/map.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index b1dad76215ed..e1004d825392 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -252,7 +252,7 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val,
 		val[i] = strtoul(argv[i], &endptr, 0);
 		if (*endptr) {
 			err("error parsing byte: %s\n", argv[i]);
-			break;
+			return NULL;
 		}
 		i++;
 	}
-- 
cgit v1.2.3


From 9e2308c133a92ff98d1397149c8483858bcf8fc0 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:24 -0700
Subject: tools: bpftool: print all relevant byte opcodes for "load double
 word"

The eBPF instruction permitting to load double words (8 bytes) into a
register need 8-byte long "immediate" field, and thus occupy twice the
space of other instructions. bpftool was aware of this and would
increment the instruction counter only once on meeting such instruction,
but it would only print the first four bytes of the immediate value to
load. Make it able to dump the whole 16 byte-long double instruction
instead (as would `llvm-objdump -d <program>`).

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/prog.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 355c14325622..57edbea2fbe8 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -313,20 +313,29 @@ static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
 static void dump_xlated(void *buf, unsigned int len, bool opcodes)
 {
 	struct bpf_insn *insn = buf;
+	bool double_insn = false;
 	unsigned int i;
 
 	for (i = 0; i < len / sizeof(*insn); i++) {
+		if (double_insn) {
+			double_insn = false;
+			continue;
+		}
+
+		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
+
 		printf("% 4d: ", i);
 		print_bpf_insn(print_insn, NULL, insn + i, true);
 
 		if (opcodes) {
 			printf("       ");
 			fprint_hex(stdout, insn + i, 8, " ");
+			if (double_insn && i < len - 1) {
+				printf(" ");
+				fprint_hex(stdout, insn + i + 1, 8, " ");
+			}
 			printf("\n");
 		}
-
-		if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW))
-			i++;
 	}
 }
 
-- 
cgit v1.2.3


From 8dfbc6d1d213df340e5dcfdcdc76ad9407a29273 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:25 -0700
Subject: tools: bpftool: show that `opcodes` or `file FILE` should be
 exclusive

For the `bpftool prog dump { jited | xlated } ...` command, adding
`opcodes` keyword (to request opcodes to be printed) will have no effect
if `file FILE` (to write binary output to FILE) is provided.

The manual page and the help message to be displayed in the terminal
should reflect that, and indicate that these options should be mutually
exclusive.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 8 ++++----
 tools/bpf/bpftool/prog.c                         | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 3968f0bd37db..69b3770370c8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -11,8 +11,8 @@ SYNOPSIS
 ========
 
 |	**bpftool** prog show [*PROG*]
-|	**bpftool** prog dump xlated *PROG* [file *FILE*] [opcodes]
-|	**bpftool** prog dump jited  *PROG* [file *FILE*] [opcodes]
+|	**bpftool** prog dump xlated *PROG* [{file *FILE* | opcodes }]
+|	**bpftool** prog dump jited  *PROG* [{file *FILE* | opcodes }]
 |	**bpftool** prog pin *PROG* *FILE*
 |	**bpftool** prog help
 |
@@ -28,14 +28,14 @@ DESCRIPTION
 		  Output will start with program ID followed by program type and
 		  zero or more named attributes (depending on kernel version).
 
-	**bpftool prog dump xlated** *PROG* [**file** *FILE*] [**opcodes**]
+	**bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** }]
 		  Dump eBPF instructions of the program from the kernel.
 		  If *FILE* is specified image will be written to a file,
 		  otherwise it will be disassembled and printed to stdout.
 
 		  **opcodes** controls if raw opcodes will be printed.
 
-	**bpftool prog dump jited**  *PROG* [**file** *FILE*] [**opcodes**]
+	**bpftool prog dump jited**  *PROG* [{ **file** *FILE* | **opcodes** }]
 		  Dump jited image (host machine code) of the program.
 		  If *FILE* is specified image will be written to a file,
 		  otherwise it will be disassembled and printed to stdout.
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 57edbea2fbe8..7838206a455b 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -469,8 +469,8 @@ static int do_help(int argc, char **argv)
 {
 	fprintf(stderr,
 		"Usage: %s %s show [PROG]\n"
-		"       %s %s dump xlated PROG [file FILE] [opcodes]\n"
-		"       %s %s dump jited  PROG [file FILE] [opcodes]\n"
+		"       %s %s dump xlated PROG [{ file FILE | opcodes }]\n"
+		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
 		"       %s %s help\n"
 		"\n"
-- 
cgit v1.2.3


From 821cfbb0dcfbb24506dc6958361ca2b80b928049 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 19 Oct 2017 15:46:26 -0700
Subject: tools: bpftool: add a command to display bpftool version

This command can be used to print the version of the tool, which is in
fact the version from Linux taken from usr/include/linux/version.h.

Example usage:

    $ bpftool version
    bpftool v4.14.0

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool.rst |  2 ++
 tools/bpf/bpftool/main.c                    | 14 +++++++++++++-
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index f1df1893fb54..45ad8baf1915 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -14,6 +14,8 @@ SYNOPSIS
 
 	**bpftool** batch file *FILE*
 
+	**bpftool** version
+
 	*OBJECT* := { **map** | **program** }
 
 	*MAP-COMMANDS* :=
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 8662199ee050..814d19e1b53f 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -37,6 +37,7 @@
 #include <ctype.h>
 #include <errno.h>
 #include <linux/bpf.h>
+#include <linux/version.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -62,13 +63,23 @@ static int do_help(int argc, char **argv)
 	fprintf(stderr,
 		"Usage: %s OBJECT { COMMAND | help }\n"
 		"       %s batch file FILE\n"
+		"       %s version\n"
 		"\n"
 		"       OBJECT := { prog | map }\n",
-		bin_name, bin_name);
+		bin_name, bin_name, bin_name);
 
 	return 0;
 }
 
+static int do_version(int argc, char **argv)
+{
+	printf("%s v%d.%d.%d\n", bin_name,
+	       LINUX_VERSION_CODE >> 16,
+	       LINUX_VERSION_CODE >> 8 & 0xf,
+	       LINUX_VERSION_CODE & 0xf);
+	return 0;
+}
+
 int cmd_select(const struct cmd *cmds, int argc, char **argv,
 	       int (*help)(int argc, char **argv))
 {
@@ -128,6 +139,7 @@ static const struct cmd cmds[] = {
 	{ "batch",	do_batch },
 	{ "prog",	do_prog },
 	{ "map",	do_map },
+	{ "version",	do_version },
 	{ 0 }
 };
 
-- 
cgit v1.2.3


From cd86d1fd21025fdd6daf23d1288da405e7ad0ec6 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Fri, 20 Oct 2017 11:05:40 -0700
Subject: bpf: Adding helper function bpf_getsockops

Adding support for helper function bpf_getsockops to socket_ops BPF
programs. This patch only supports TCP_CONGESTION.

Signed-off-by: Vlad Vysotsky <vlad@cs.ucla.edu>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h                  | 19 ++++++++++---
 net/core/filter.c                         | 46 ++++++++++++++++++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  3 ++
 3 files changed, 63 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1aca744c220f..f650346aaa1a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -613,12 +613,22 @@ union bpf_attr {
  * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
  *     Calls setsockopt. Not all opts are available, only those with
  *     integer optvals plus TCP_CONGESTION.
- *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     Supported levels: SOL_SOCKET and IPPROTO_TCP
  *     @bpf_socket: pointer to bpf_socket
- *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @level: SOL_SOCKET or IPPROTO_TCP
  *     @optname: option name
  *     @optval: pointer to option value
- *     @optlen: length of optval in byes
+ *     @optlen: length of optval in bytes
+ *     Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls getsockopt. Not all opts are available.
+ *     Supported levels: IPPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -721,7 +731,8 @@ union bpf_attr {
 	FN(sock_map_update),		\
 	FN(xdp_adjust_meta),		\
 	FN(perf_event_read_value),	\
-	FN(perf_prog_read_value),
+	FN(perf_prog_read_value),	\
+	FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/net/core/filter.c b/net/core/filter.c
index 09e011f20291..ccf62f44140a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3273,7 +3273,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 
 static const struct bpf_func_proto bpf_setsockopt_proto = {
 	.func		= bpf_setsockopt,
-	.gpl_only	= true,
+	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_ANYTHING,
@@ -3282,6 +3282,48 @@ static const struct bpf_func_proto bpf_setsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	struct sock *sk = bpf_sock->sk;
+	int ret = 0;
+
+	if (!sk_fullsock(sk))
+		goto err_clear;
+
+#ifdef CONFIG_INET
+	if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
+		if (optname == TCP_CONGESTION) {
+			struct inet_connection_sock *icsk = inet_csk(sk);
+
+			if (!icsk->icsk_ca_ops || optlen <= 1)
+				goto err_clear;
+			strncpy(optval, icsk->icsk_ca_ops->name, optlen);
+			optval[optlen - 1] = 0;
+		} else {
+			goto err_clear;
+		}
+	} else {
+		goto err_clear;
+	}
+	return ret;
+#endif
+err_clear:
+	memset(optval, 0, optlen);
+	return -EINVAL;
+}
+
+static const struct bpf_func_proto bpf_getsockopt_proto = {
+	.func		= bpf_getsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3460,6 +3502,8 @@ static const struct bpf_func_proto *
 	switch (func_id) {
 	case BPF_FUNC_setsockopt:
 		return &bpf_setsockopt_proto;
+	case BPF_FUNC_getsockopt:
+		return &bpf_getsockopt_proto;
 	case BPF_FUNC_sock_map_update:
 		return &bpf_sock_map_update_proto;
 	default:
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index e25dbf6038cf..609514f74482 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -67,6 +67,9 @@ static int (*bpf_xdp_adjust_meta)(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_getsockopt)(void *ctx, int level, int optname, void *optval,
+			     int optlen) =
+	(void *) BPF_FUNC_getsockopt;
 static int (*bpf_sk_redirect_map)(void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
-- 
cgit v1.2.3


From e27afb84b4680570b64c958dfcba9e0b3da92fc9 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Sun, 22 Oct 2017 10:29:06 -0700
Subject: selftests/bpf: fix broken build of test_maps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fix multiple build errors and warnings

1.
test_maps.c: In function ‘test_map_rdonly’:
test_maps.c:1051:30: error: ‘BPF_F_RDONLY’ undeclared (first use in this function)
        MAP_SIZE, map_flags | BPF_F_RDONLY);

2.
test_maps.c:1048:6: warning: unused variable ‘i’ [-Wunused-variable]
  int i, fd, key = 0, value = 0;

3.
test_maps.c:1087:2: error: called object is not a function or function pointer
  assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);

4.
./bpf_helpers.h:72:11: error: use of undeclared identifier 'BPF_FUNC_getsockopt'
        (void *) BPF_FUNC_getsockopt;

Fixes: e043325b3087 ("bpf: Add tests for eBPF file mode")
Fixes: 6e71b04a8224 ("bpf: Add file mode configuration into bpf maps")
Fixes: cd86d1fd2102 ("bpf: Adding helper function bpf_getsockops")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/include/uapi/linux/bpf.h          | 62 ++++++++++++++++++++++++++++-----
 tools/testing/selftests/bpf/test_maps.c |  6 ++--
 2 files changed, 57 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 850a5497dcc3..f650346aaa1a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -218,6 +218,10 @@ enum bpf_attach_type {
 
 #define BPF_OBJ_NAME_LEN 16U
 
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY		(1U << 3)
+#define BPF_F_WRONLY		(1U << 4)
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -260,6 +264,7 @@ union bpf_attr {
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
+		__u32		file_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -287,6 +292,7 @@ union bpf_attr {
 			__u32		map_id;
 		};
 		__u32		next_id;
+		__u32		open_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -607,12 +613,22 @@ union bpf_attr {
  * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
  *     Calls setsockopt. Not all opts are available, only those with
  *     integer optvals plus TCP_CONGESTION.
- *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     Supported levels: SOL_SOCKET and IPPROTO_TCP
  *     @bpf_socket: pointer to bpf_socket
- *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @level: SOL_SOCKET or IPPROTO_TCP
  *     @optname: option name
  *     @optval: pointer to option value
- *     @optlen: length of optval in byes
+ *     @optlen: length of optval in bytes
+ *     Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls getsockopt. Not all opts are available.
+ *     Supported levels: IPPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -623,10 +639,9 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(skb, map, key, flags)
+ * int bpf_sk_redirect_map(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
@@ -643,6 +658,21 @@ union bpf_attr {
  *     @xdp_md: pointer to xdp_md
  *     @delta: An positive/negative integer to be added to xdp_md.data_meta
  *     Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ *     read perf event counter value and perf event enabled/running time
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ *     read perf prog attached perf event counter and enabled/running time
+ *     @ctx: pointer to ctx
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return : 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -701,7 +731,8 @@ union bpf_attr {
 	FN(sock_map_update),		\
 	FN(xdp_adjust_meta),		\
 	FN(perf_event_read_value),	\
-	FN(perf_prog_read_value),
+	FN(perf_prog_read_value),	\
+	FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -745,7 +776,9 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
 #define BPF_F_INDEX_MASK		0xffffffffULL
 #define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -873,7 +906,7 @@ struct bpf_prog_info {
 	__u32 created_by_uid;
 	__u32 nr_map_ids;
 	__aligned_u64 map_ids;
-	char  name[BPF_OBJ_NAME_LEN];
+	char name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -933,9 +966,22 @@ enum {
 	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
 					 * needs ECN
 					 */
+	BPF_SOCK_OPS_BASE_RTT,		/* Get base RTT. The correct value is
+					 * based on the path and may be
+					 * dependent on the congestion control
+					 * algorithm. In general it indicates
+					 * a congestion threshold. RTTs above
+					 * this indicate congestion
+					 */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
 #define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
 
+struct bpf_perf_event_value {
+	__u64 counter;
+	__u64 enabled;
+	__u64 running;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 057da0cba517..040356ecc862 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1045,7 +1045,7 @@ static void test_map_parallel(void)
 
 static void test_map_rdonly(void)
 {
-	int i, fd, key = 0, value = 0;
+	int fd, key = 0, value = 0;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
 			    MAP_SIZE, map_flags | BPF_F_RDONLY);
@@ -1068,7 +1068,7 @@ static void test_map_rdonly(void)
 
 static void test_map_wronly(void)
 {
-	int i, fd, key = 0, value = 0;
+	int fd, key = 0, value = 0;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
 			    MAP_SIZE, map_flags | BPF_F_WRONLY);
@@ -1081,7 +1081,7 @@ static void test_map_wronly(void)
 	key = 1;
 	value = 1234;
 	/* Insert key=1 element. */
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0)
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
 	/* Check that key=2 is not found. */
 	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
-- 
cgit v1.2.3


From b66e907cfee240a09a4b5aabf950a0d4c8da8d32 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:05 -0700
Subject: tools: bpftool: copy JSON writer from iproute2 repository

In prevision of following commits, supposed to add JSON output to the
tool, two files are copied from the iproute2 repository (taken at commit
268a9eee985f): lib/json_writer.c and include/json_writer.h.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/json_writer.c | 348 ++++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/json_writer.h |  70 ++++++++
 2 files changed, 418 insertions(+)
 create mode 100644 tools/bpf/bpftool/json_writer.c
 create mode 100644 tools/bpf/bpftool/json_writer.h

(limited to 'tools')

diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
new file mode 100644
index 000000000000..6b77d288cce2
--- /dev/null
+++ b/tools/bpf/bpftool/json_writer.c
@@ -0,0 +1,348 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
+#include <assert.h>
+#include <malloc.h>
+#include <inttypes.h>
+#include <stdint.h>
+
+#include "json_writer.h"
+
+struct json_writer {
+	FILE		*out;	/* output file */
+	unsigned	depth;  /* nesting */
+	bool		pretty; /* optional whitepace */
+	char		sep;	/* either nul or comma */
+};
+
+/* indentation for pretty print */
+static void jsonw_indent(json_writer_t *self)
+{
+	unsigned i;
+	for (i = 0; i < self->depth; ++i)
+		fputs("    ", self->out);
+}
+
+/* end current line and indent if pretty printing */
+static void jsonw_eol(json_writer_t *self)
+{
+	if (!self->pretty)
+		return;
+
+	putc('\n', self->out);
+	jsonw_indent(self);
+}
+
+/* If current object is not empty print a comma */
+static void jsonw_eor(json_writer_t *self)
+{
+	if (self->sep != '\0')
+		putc(self->sep, self->out);
+	self->sep = ',';
+}
+
+
+/* Output JSON encoded string */
+/* Handles C escapes, does not do Unicode */
+static void jsonw_puts(json_writer_t *self, const char *str)
+{
+	putc('"', self->out);
+	for (; *str; ++str)
+		switch (*str) {
+		case '\t':
+			fputs("\\t", self->out);
+			break;
+		case '\n':
+			fputs("\\n", self->out);
+			break;
+		case '\r':
+			fputs("\\r", self->out);
+			break;
+		case '\f':
+			fputs("\\f", self->out);
+			break;
+		case '\b':
+			fputs("\\b", self->out);
+			break;
+		case '\\':
+			fputs("\\n", self->out);
+			break;
+		case '"':
+			fputs("\\\"", self->out);
+			break;
+		case '\'':
+			fputs("\\\'", self->out);
+			break;
+		default:
+			putc(*str, self->out);
+		}
+	putc('"', self->out);
+}
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f)
+{
+	json_writer_t *self = malloc(sizeof(*self));
+	if (self) {
+		self->out = f;
+		self->depth = 0;
+		self->pretty = false;
+		self->sep = '\0';
+	}
+	return self;
+}
+
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p)
+{
+	json_writer_t *self = *self_p;
+
+	assert(self->depth == 0);
+	fputs("\n", self->out);
+	fflush(self->out);
+	free(self);
+	*self_p = NULL;
+}
+
+void jsonw_pretty(json_writer_t *self, bool on)
+{
+	self->pretty = on;
+}
+
+/* Basic blocks */
+static void jsonw_begin(json_writer_t *self, int c)
+{
+	jsonw_eor(self);
+	putc(c, self->out);
+	++self->depth;
+	self->sep = '\0';
+}
+
+static void jsonw_end(json_writer_t *self, int c)
+{
+	assert(self->depth > 0);
+
+	--self->depth;
+	if (self->sep != '\0')
+		jsonw_eol(self);
+	putc(c, self->out);
+	self->sep = ',';
+}
+
+
+/* Add a JSON property name */
+void jsonw_name(json_writer_t *self, const char *name)
+{
+	jsonw_eor(self);
+	jsonw_eol(self);
+	self->sep = '\0';
+	jsonw_puts(self, name);
+	putc(':', self->out);
+	if (self->pretty)
+		putc(' ', self->out);
+}
+
+void jsonw_printf(json_writer_t *self, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	jsonw_eor(self);
+	vfprintf(self->out, fmt, ap);
+	va_end(ap);
+}
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self)
+{
+	jsonw_begin(self, '{');
+}
+
+void jsonw_end_object(json_writer_t *self)
+{
+	jsonw_end(self, '}');
+}
+
+void jsonw_start_array(json_writer_t *self)
+{
+	jsonw_begin(self, '[');
+}
+
+void jsonw_end_array(json_writer_t *self)
+{
+	jsonw_end(self, ']');
+}
+
+/* JSON value types */
+void jsonw_string(json_writer_t *self, const char *value)
+{
+	jsonw_eor(self);
+	jsonw_puts(self, value);
+}
+
+void jsonw_bool(json_writer_t *self, bool val)
+{
+	jsonw_printf(self, "%s", val ? "true" : "false");
+}
+
+void jsonw_null(json_writer_t *self)
+{
+	jsonw_printf(self, "null");
+}
+
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num)
+{
+	jsonw_printf(self, fmt, num);
+}
+
+#ifdef notused
+void jsonw_float(json_writer_t *self, double num)
+{
+	jsonw_printf(self, "%g", num);
+}
+#endif
+
+void jsonw_hu(json_writer_t *self, unsigned short num)
+{
+	jsonw_printf(self, "%hu", num);
+}
+
+void jsonw_uint(json_writer_t *self, uint64_t num)
+{
+	jsonw_printf(self, "%"PRIu64, num);
+}
+
+void jsonw_lluint(json_writer_t *self, unsigned long long int num)
+{
+	jsonw_printf(self, "%llu", num);
+}
+
+void jsonw_int(json_writer_t *self, int64_t num)
+{
+	jsonw_printf(self, "%"PRId64, num);
+}
+
+/* Basic name/value objects */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val)
+{
+	jsonw_name(self, prop);
+	jsonw_string(self, val);
+}
+
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool val)
+{
+	jsonw_name(self, prop);
+	jsonw_bool(self, val);
+}
+
+#ifdef notused
+void jsonw_float_field(json_writer_t *self, const char *prop, double val)
+{
+	jsonw_name(self, prop);
+	jsonw_float(self, val);
+}
+#endif
+
+void jsonw_float_field_fmt(json_writer_t *self,
+			   const char *prop,
+			   const char *fmt,
+			   double val)
+{
+	jsonw_name(self, prop);
+	jsonw_float_fmt(self, fmt, val);
+}
+
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num)
+{
+	jsonw_name(self, prop);
+	jsonw_uint(self, num);
+}
+
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num)
+{
+	jsonw_name(self, prop);
+	jsonw_hu(self, num);
+}
+
+void jsonw_lluint_field(json_writer_t *self,
+			const char *prop,
+			unsigned long long int num)
+{
+	jsonw_name(self, prop);
+	jsonw_lluint(self, num);
+}
+
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num)
+{
+	jsonw_name(self, prop);
+	jsonw_int(self, num);
+}
+
+void jsonw_null_field(json_writer_t *self, const char *prop)
+{
+	jsonw_name(self, prop);
+	jsonw_null(self);
+}
+
+#ifdef TEST
+int main(int argc, char **argv)
+{
+	json_writer_t *wr = jsonw_new(stdout);
+
+	jsonw_start_object(wr);
+	jsonw_pretty(wr, true);
+	jsonw_name(wr, "Vyatta");
+	jsonw_start_object(wr);
+	jsonw_string_field(wr, "url", "http://vyatta.com");
+	jsonw_uint_field(wr, "downloads", 2000000ul);
+	jsonw_float_field(wr, "stock", 8.16);
+
+	jsonw_name(wr, "ARGV");
+	jsonw_start_array(wr);
+	while (--argc)
+		jsonw_string(wr, *++argv);
+	jsonw_end_array(wr);
+
+	jsonw_name(wr, "empty");
+	jsonw_start_array(wr);
+	jsonw_end_array(wr);
+
+	jsonw_name(wr, "NIL");
+	jsonw_start_object(wr);
+	jsonw_end_object(wr);
+
+	jsonw_null_field(wr, "my_null");
+
+	jsonw_name(wr, "special chars");
+	jsonw_start_array(wr);
+	jsonw_string_field(wr, "slash", "/");
+	jsonw_string_field(wr, "newline", "\n");
+	jsonw_string_field(wr, "tab", "\t");
+	jsonw_string_field(wr, "ff", "\f");
+	jsonw_string_field(wr, "quote", "\"");
+	jsonw_string_field(wr, "tick", "\'");
+	jsonw_string_field(wr, "backslash", "\\");
+	jsonw_end_array(wr);
+
+	jsonw_end_object(wr);
+
+	jsonw_end_object(wr);
+	jsonw_destroy(&wr);
+	return 0;
+}
+
+#endif
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
new file mode 100644
index 000000000000..1516aafba59d
--- /dev/null
+++ b/tools/bpf/bpftool/json_writer.h
@@ -0,0 +1,70 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#ifndef _JSON_WRITER_H_
+#define _JSON_WRITER_H_
+
+#include <stdbool.h>
+#include <stdint.h>
+
+/* Opaque class structure */
+typedef struct json_writer json_writer_t;
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f);
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p);
+
+/* Cause output to have pretty whitespace */
+void jsonw_pretty(json_writer_t *self, bool on);
+
+/* Add property name */
+void jsonw_name(json_writer_t *self, const char *name);
+
+/* Add value  */
+void jsonw_printf(json_writer_t *self, const char *fmt, ...);
+void jsonw_string(json_writer_t *self, const char *value);
+void jsonw_bool(json_writer_t *self, bool value);
+void jsonw_float(json_writer_t *self, double number);
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num);
+void jsonw_uint(json_writer_t *self, uint64_t number);
+void jsonw_hu(json_writer_t *self, unsigned short number);
+void jsonw_int(json_writer_t *self, int64_t number);
+void jsonw_null(json_writer_t *self);
+void jsonw_lluint(json_writer_t *self, unsigned long long int num);
+
+/* Useful Combinations of name and value */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
+void jsonw_float_field(json_writer_t *self, const char *prop, double num);
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num);
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num);
+void jsonw_null_field(json_writer_t *self, const char *prop);
+void jsonw_lluint_field(json_writer_t *self, const char *prop,
+			unsigned long long int num);
+void jsonw_float_field_fmt(json_writer_t *self, const char *prop,
+			   const char *fmt, double val);
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self);
+void jsonw_end_object(json_writer_t *self);
+
+void jsonw_start_array(json_writer_t *self);
+void jsonw_end_array(json_writer_t *self);
+
+/* Override default exception handling */
+typedef void (jsonw_err_handler_fn)(const char *);
+
+#endif /* _JSON_WRITER_H_ */
-- 
cgit v1.2.3


From a2bc2e5c2c0604bf5366b5e56ef46335adaf7491 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:06 -0700
Subject: tools: bpftool: add option parsing to bpftool, --help and --version

Add an option parsing facility to bpftool, in prevision of future
options for demanding JSON output. Currently, two options are added:
--help and --version, that act the same as the respective commands
`help` and `version`.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst  |  8 +++++++
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  8 +++++++
 tools/bpf/bpftool/Documentation/bpftool.rst      |  8 +++++++
 tools/bpf/bpftool/main.c                         | 27 +++++++++++++++++++++++-
 4 files changed, 50 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index ff63e89e4b6c..5210c4fab356 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -68,6 +68,14 @@ DESCRIPTION
 	**bpftool map help**
 		  Print short help message.
 
+OPTIONS
+=======
+	-h, --help
+		  Print short generic help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
 EXAMPLES
 ========
 **# bpftool map show**
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 69b3770370c8..6620a81d9dc9 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -50,6 +50,14 @@ DESCRIPTION
 	**bpftool prog help**
 		  Print short help message.
 
+OPTIONS
+=======
+	-h, --help
+		  Print short generic help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
 EXAMPLES
 ========
 **# bpftool prog show**
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 45ad8baf1915..9c04cd6677bd 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -31,6 +31,14 @@ DESCRIPTION
 	Note that format of the output of all tools is not guaranteed to be
 	stable and should not be depended upon.
 
+OPTIONS
+=======
+	-h, --help
+		  Print short help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
 SEE ALSO
 ========
 	**bpftool-map**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 814d19e1b53f..613e3c75f78a 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -36,6 +36,7 @@
 #include <bfd.h>
 #include <ctype.h>
 #include <errno.h>
+#include <getopt.h>
 #include <linux/bpf.h>
 #include <linux/version.h>
 #include <stdio.h>
@@ -215,8 +216,32 @@ err_close:
 
 int main(int argc, char **argv)
 {
+	static const struct option options[] = {
+		{ "help",	no_argument,	NULL,	'h' },
+		{ "version",	no_argument,	NULL,	'V' },
+		{ 0 }
+	};
+	int opt;
+
+	last_do_help = do_help;
 	bin_name = argv[0];
-	NEXT_ARG();
+
+	while ((opt = getopt_long(argc, argv, "Vh",
+				  options, NULL)) >= 0) {
+		switch (opt) {
+		case 'V':
+			return do_version(argc, argv);
+		case 'h':
+			return do_help(argc, argv);
+		default:
+			usage();
+		}
+	}
+
+	argc -= optind;
+	argv += optind;
+	if (argc < 0)
+		usage();
 
 	bfd_init();
 
-- 
cgit v1.2.3


From d35efba99d9221d9fe1715a23247ad9b703544ec Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:07 -0700
Subject: tools: bpftool: introduce --json and --pretty options

These two options can be used to ask for a JSON output (--j or -json),
and to make this JSON human-readable (-p or --pretty).

A json_writer object is created when JSON is required, and will be used
in follow-up commits to produce JSON output.

Note that --pretty implies --json.

Update for the manual pages and interactive help messages comes in a
later patch of the series.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/main.c | 33 ++++++++++++++++++++++++++++++---
 tools/bpf/bpftool/main.h |  5 +++++
 2 files changed, 35 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 613e3c75f78a..14bfc17cd4de 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -51,6 +51,9 @@ const char *bin_name;
 static int last_argc;
 static char **last_argv;
 static int (*last_do_help)(int argc, char **argv);
+json_writer_t *json_wtr;
+bool pretty_output;
+bool json_output;
 
 void usage(void)
 {
@@ -217,22 +220,32 @@ err_close:
 int main(int argc, char **argv)
 {
 	static const struct option options[] = {
+		{ "json",	no_argument,	NULL,	'j' },
 		{ "help",	no_argument,	NULL,	'h' },
+		{ "pretty",	no_argument,	NULL,	'p' },
 		{ "version",	no_argument,	NULL,	'V' },
 		{ 0 }
 	};
-	int opt;
+	int opt, ret;
 
 	last_do_help = do_help;
+	pretty_output = false;
+	json_output = false;
 	bin_name = argv[0];
 
-	while ((opt = getopt_long(argc, argv, "Vh",
+	while ((opt = getopt_long(argc, argv, "Vhpj",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
 			return do_version(argc, argv);
 		case 'h':
 			return do_help(argc, argv);
+		case 'p':
+			pretty_output = true;
+			/* fall through */
+		case 'j':
+			json_output = true;
+			break;
 		default:
 			usage();
 		}
@@ -243,7 +256,21 @@ int main(int argc, char **argv)
 	if (argc < 0)
 		usage();
 
+	if (json_output) {
+		json_wtr = jsonw_new(stdout);
+		if (!json_wtr) {
+			err("failed to create JSON writer\n");
+			return -1;
+		}
+		jsonw_pretty(json_wtr, pretty_output);
+	}
+
 	bfd_init();
 
-	return cmd_select(cmds, argc, argv, do_help);
+	ret = cmd_select(cmds, argc, argv, do_help);
+
+	if (json_output)
+		jsonw_destroy(&json_wtr);
+
+	return ret;
 }
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 41e6c7d3fcad..15927fc9fb31 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -43,6 +43,8 @@
 #include <linux/bpf.h>
 #include <linux/kernel.h>
 
+#include "json_writer.h"
+
 #define err(msg...)	fprintf(stderr, "Error: " msg)
 #define warn(msg...)	fprintf(stderr, "Warning: " msg)
 #define info(msg...)	fprintf(stderr, msg)
@@ -66,6 +68,9 @@ enum bpf_obj_type {
 
 extern const char *bin_name;
 
+extern json_writer_t *json_wtr;
+extern bool json_output;
+
 bool is_prefix(const char *pfx, const char *str);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __attribute__((noreturn));
-- 
cgit v1.2.3


From 743cc665d5f62d2c75eceb59c461e653ad6ea58c Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:08 -0700
Subject: tools: bpftool: add JSON output for `bpftool prog show *` command

Reuse the json_writer API introduced in an earlier commit to make
bpftool able to generate JSON output on `bpftool prog show *` commands.

For readability, the code from show_prog() has been split into two
functions, one for plain output, one for JSON.

Outputs from sample programs have been successfully tested against a
JSON validator.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/prog.c | 139 ++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 107 insertions(+), 32 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 7838206a455b..f373f2baef5a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -195,51 +195,100 @@ static void show_prog_maps(int fd, u32 num_maps)
 	if (err || !info.nr_map_ids)
 		return;
 
-	printf("  map_ids ");
-	for (i = 0; i < info.nr_map_ids; i++)
-		printf("%u%s", map_ids[i],
-		       i == info.nr_map_ids - 1 ? "" : ",");
+	if (json_output) {
+		jsonw_name(json_wtr, "map_ids");
+		jsonw_start_array(json_wtr);
+		for (i = 0; i < info.nr_map_ids; i++)
+			jsonw_uint(json_wtr, map_ids[i]);
+		jsonw_end_array(json_wtr);
+	} else {
+		printf("  map_ids ");
+		for (i = 0; i < info.nr_map_ids; i++)
+			printf("%u%s", map_ids[i],
+			       i == info.nr_map_ids - 1 ? "" : ",");
+	}
 }
 
-static int show_prog(int fd)
+static void print_prog_json(struct bpf_prog_info *info, int fd)
 {
-	struct bpf_prog_info info = {};
-	__u32 len = sizeof(info);
 	char *memlock;
-	int err;
 
-	err = bpf_obj_get_info_by_fd(fd, &info, &len);
-	if (err) {
-		err("can't get prog info: %s\n", strerror(errno));
-		return -1;
+	jsonw_start_object(json_wtr);
+	jsonw_uint_field(json_wtr, "id", info->id);
+	if (info->type < ARRAY_SIZE(prog_type_name))
+		jsonw_string_field(json_wtr, "type",
+				   prog_type_name[info->type]);
+	else
+		jsonw_uint_field(json_wtr, "type", info->type);
+
+	if (*info->name)
+		jsonw_string_field(json_wtr, "name", info->name);
+
+	jsonw_name(json_wtr, "tag");
+	jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
+		     info->tag[0], info->tag[1], info->tag[2], info->tag[3],
+		     info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
+
+	if (info->load_time) {
+		char buf[32];
+
+		print_boot_time(info->load_time, buf, sizeof(buf));
+
+		/* Piggy back on load_time, since 0 uid is a valid one */
+		jsonw_string_field(json_wtr, "loaded_at", buf);
+		jsonw_uint_field(json_wtr, "uid", info->created_by_uid);
 	}
 
-	printf("%u: ", info.id);
-	if (info.type < ARRAY_SIZE(prog_type_name))
-		printf("%s  ", prog_type_name[info.type]);
+	jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len);
+
+	if (info->jited_prog_len) {
+		jsonw_bool_field(json_wtr, "jited", true);
+		jsonw_uint_field(json_wtr, "bytes_jited", info->jited_prog_len);
+	} else {
+		jsonw_bool_field(json_wtr, "jited", false);
+	}
+
+	memlock = get_fdinfo(fd, "memlock");
+	if (memlock)
+		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+	free(memlock);
+
+	if (info->nr_map_ids)
+		show_prog_maps(fd, info->nr_map_ids);
+
+	jsonw_end_object(json_wtr);
+}
+
+static void print_prog_plain(struct bpf_prog_info *info, int fd)
+{
+	char *memlock;
+
+	printf("%u: ", info->id);
+	if (info->type < ARRAY_SIZE(prog_type_name))
+		printf("%s  ", prog_type_name[info->type]);
 	else
-		printf("type %u  ", info.type);
+		printf("type %u  ", info->type);
 
-	if (*info.name)
-		printf("name %s  ", info.name);
+	if (*info->name)
+		printf("name %s  ", info->name);
 
 	printf("tag ");
-	fprint_hex(stdout, info.tag, BPF_TAG_SIZE, "");
+	fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
 	printf("\n");
 
-	if (info.load_time) {
+	if (info->load_time) {
 		char buf[32];
 
-		print_boot_time(info.load_time, buf, sizeof(buf));
+		print_boot_time(info->load_time, buf, sizeof(buf));
 
 		/* Piggy back on load_time, since 0 uid is a valid one */
-		printf("\tloaded_at %s  uid %u\n", buf, info.created_by_uid);
+		printf("\tloaded_at %s  uid %u\n", buf, info->created_by_uid);
 	}
 
-	printf("\txlated %uB", info.xlated_prog_len);
+	printf("\txlated %uB", info->xlated_prog_len);
 
-	if (info.jited_prog_len)
-		printf("  jited %uB", info.jited_prog_len);
+	if (info->jited_prog_len)
+		printf("  jited %uB", info->jited_prog_len);
 	else
 		printf("  not jited");
 
@@ -248,16 +297,35 @@ static int show_prog(int fd)
 		printf("  memlock %sB", memlock);
 	free(memlock);
 
-	if (info.nr_map_ids)
-		show_prog_maps(fd, info.nr_map_ids);
+	if (info->nr_map_ids)
+		show_prog_maps(fd, info->nr_map_ids);
 
 	printf("\n");
+}
+
+static int show_prog(int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	int err;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err) {
+		err("can't get prog info: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (json_output)
+		print_prog_json(&info, fd);
+	else
+		print_prog_plain(&info, fd);
 
 	return 0;
 }
 
 static int do_show(int argc, char **argv)
-{	__u32 id = 0;
+{
+	__u32 id = 0;
 	int err;
 	int fd;
 
@@ -272,6 +340,8 @@ static int do_show(int argc, char **argv)
 	if (argc)
 		return BAD_ARG();
 
+	if (json_output)
+		jsonw_start_array(json_wtr);
 	while (true) {
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
@@ -282,23 +352,28 @@ static int do_show(int argc, char **argv)
 			err("can't get next program: %s\n", strerror(errno));
 			if (errno == EINVAL)
 				err("kernel too old?\n");
-			return -1;
+			err = -1;
+			break;
 		}
 
 		fd = bpf_prog_get_fd_by_id(id);
 		if (fd < 0) {
 			err("can't get prog by id (%u): %s\n",
 			    id, strerror(errno));
-			return -1;
+			err = -1;
+			break;
 		}
 
 		err = show_prog(fd);
 		close(fd);
 		if (err)
-			return err;
+			break;
 	}
 
-	return 0;
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	return err;
 }
 
 static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
-- 
cgit v1.2.3


From 107f041212c1dfd3bf72b01c0d2013e98b6f32c2 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:09 -0700
Subject: tools: bpftool: add JSON output for `bpftool prog dump jited *`
 command

Reuse the json_writer API introduced in an earlier commit to make
bpftool able to generate JSON output on `bpftool prog show *` commands.
A new printing function is created to be passed as an argument to the
disassembler.

Similarly to plain output, opcodes are printed on request.

Outputs from sample programs have been successfully tested against a
JSON validator.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/jit_disasm.c | 86 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 80 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 70e480b59e9d..5937e134e408 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -10,6 +10,7 @@
  * Licensed under the GNU General Public License, version 2.0 (GPLv2)
  */
 
+#include <stdarg.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -21,6 +22,9 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 
+#include "json_writer.h"
+#include "main.h"
+
 static void get_exec_path(char *tpath, size_t size)
 {
 	ssize_t len;
@@ -39,6 +43,38 @@ static void get_exec_path(char *tpath, size_t size)
 	free(path);
 }
 
+static int oper_count;
+static int fprintf_json(void *out, const char *fmt, ...)
+{
+	va_list ap;
+	char *s;
+
+	va_start(ap, fmt);
+	if (!oper_count) {
+		int i;
+
+		s = va_arg(ap, char *);
+
+		/* Strip trailing spaces */
+		i = strlen(s) - 1;
+		while (s[i] == ' ')
+			s[i--] = '\0';
+
+		jsonw_string_field(json_wtr, "operation", s);
+		jsonw_name(json_wtr, "operands");
+		jsonw_start_array(json_wtr);
+		oper_count++;
+	} else if (!strcmp(fmt, ",")) {
+		   /* Skip */
+	} else {
+		s = va_arg(ap, char *);
+		jsonw_string(json_wtr, s);
+		oper_count++;
+	}
+	va_end(ap);
+	return 0;
+}
+
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
 {
 	disassembler_ftype disassemble;
@@ -57,7 +93,12 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
 	assert(bfdf);
 	assert(bfd_check_format(bfdf, bfd_object));
 
-	init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf);
+	if (json_output)
+		init_disassemble_info(&info, stdout,
+				      (fprintf_ftype) fprintf_json);
+	else
+		init_disassemble_info(&info, stdout,
+				      (fprintf_ftype) fprintf);
 	info.arch = bfd_get_arch(bfdf);
 	info.mach = bfd_get_mach(bfdf);
 	info.buffer = image;
@@ -68,20 +109,53 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
 	disassemble = disassembler(bfdf);
 	assert(disassemble);
 
+	if (json_output)
+		jsonw_start_array(json_wtr);
 	do {
-		printf("%4x:\t", pc);
+		if (json_output) {
+			jsonw_start_object(json_wtr);
+			oper_count = 0;
+			jsonw_name(json_wtr, "pc");
+			jsonw_printf(json_wtr, "\"0x%x\"", pc);
+		} else {
+			printf("%4x:\t", pc);
+		}
 
 		count = disassemble(pc, &info);
+		if (json_output) {
+			/* Operand array, was started in fprintf_json. Before
+			 * that, make sure we have a _null_ value if no operand
+			 * other than operation code was present.
+			 */
+			if (oper_count == 1)
+				jsonw_null(json_wtr);
+			jsonw_end_array(json_wtr);
+		}
 
 		if (opcodes) {
-			printf("\n\t");
-			for (i = 0; i < count; ++i)
-				printf("%02x ", (uint8_t) image[pc + i]);
+			if (json_output) {
+				jsonw_name(json_wtr, "opcodes");
+				jsonw_start_array(json_wtr);
+				for (i = 0; i < count; ++i)
+					jsonw_printf(json_wtr, "\"0x%02hhx\"",
+						     (uint8_t)image[pc + i]);
+				jsonw_end_array(json_wtr);
+			} else {
+				printf("\n\t");
+				for (i = 0; i < count; ++i)
+					printf("%02x ",
+					       (uint8_t)image[pc + i]);
+			}
 		}
-		printf("\n");
+		if (json_output)
+			jsonw_end_object(json_wtr);
+		else
+			printf("\n");
 
 		pc += count;
 	} while (count > 0 && pc < len);
+	if (json_output)
+		jsonw_end_array(json_wtr);
 
 	bfd_close(bfdf);
 }
-- 
cgit v1.2.3


From f05e2c32f715985f54265b1e237b5cce1b576c71 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:10 -0700
Subject: tools: bpftool: add JSON output for `bpftool prog dump xlated *`
 command

Add a new printing function to dump translated eBPF instructions as
JSON. As for plain output, opcodes are printed only on request (when
`opcodes` is provided on the command line).

The disassembled output is generated by the same code that is used by
the kernel verifier.

Example output:

    $ bpftool --json --pretty prog dump xlated id 1
    [{
            "disasm": "(bf) r6 = r1"
        },{
            "disasm": "(61) r7 = *(u32 *)(r6 +16)"
        },{
            "disasm": "(95) exit"
        }
    ]

    $ bpftool --json --pretty prog dump xlated id 1 opcodes
    [{
            "disasm": "(bf) r6 = r1",
            "opcodes": {
                "code": "0xbf",
                "src_reg": "0x1",
                "dst_reg": "0x6",
                "off": ["0x00","0x00"
                ],
                "imm": ["0x00","0x00","0x00","0x00"
                ]
            }
        },{
            "disasm": "(61) r7 = *(u32 *)(r6 +16)",
            "opcodes": {
                "code": "0x61",
                "src_reg": "0x6",
                "dst_reg": "0x7",
                "off": ["0x10","0x00"
                ],
                "imm": ["0x00","0x00","0x00","0x00"
                ]
            }
        },{
            "disasm": "(95) exit",
            "opcodes": {
                "code": "0x95",
                "src_reg": "0x0",
                "dst_reg": "0x0",
                "off": ["0x00","0x00"
                ],
                "imm": ["0x00","0x00","0x00","0x00"
                ]
            }
        }
    ]

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/common.c      | 10 ++++++
 tools/bpf/bpftool/json_writer.c |  8 +++++
 tools/bpf/bpftool/json_writer.h |  2 ++
 tools/bpf/bpftool/main.h        |  1 +
 tools/bpf/bpftool/prog.c        | 70 +++++++++++++++++++++++++++++++++++++++--
 5 files changed, 89 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index df8396a0c400..e7a756b8ee21 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -214,3 +214,13 @@ char *get_fdinfo(int fd, const char *key)
 	fclose(fdi);
 	return NULL;
 }
+
+void print_hex_data_json(uint8_t *data, size_t len)
+{
+	unsigned int i;
+
+	jsonw_start_array(json_wtr);
+	for (i = 0; i < len; i++)
+		jsonw_printf(json_wtr, "\"0x%02hhx\"", data[i]);
+	jsonw_end_array(json_wtr);
+}
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
index 6b77d288cce2..c6eef76322ae 100644
--- a/tools/bpf/bpftool/json_writer.c
+++ b/tools/bpf/bpftool/json_writer.c
@@ -156,6 +156,14 @@ void jsonw_name(json_writer_t *self, const char *name)
 		putc(' ', self->out);
 }
 
+void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
+{
+	jsonw_eor(self);
+	putc('"', self->out);
+	vfprintf(self->out, fmt, ap);
+	putc('"', self->out);
+}
+
 void jsonw_printf(json_writer_t *self, const char *fmt, ...)
 {
 	va_list ap;
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
index 1516aafba59d..0fa2fb1b6351 100644
--- a/tools/bpf/bpftool/json_writer.h
+++ b/tools/bpf/bpftool/json_writer.h
@@ -17,6 +17,7 @@
 
 #include <stdbool.h>
 #include <stdint.h>
+#include <stdarg.h>
 
 /* Opaque class structure */
 typedef struct json_writer json_writer_t;
@@ -33,6 +34,7 @@ void jsonw_pretty(json_writer_t *self, bool on);
 void jsonw_name(json_writer_t *self, const char *name);
 
 /* Add value  */
+void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap);
 void jsonw_printf(json_writer_t *self, const char *fmt, ...);
 void jsonw_string(json_writer_t *self, const char *value);
 void jsonw_bool(json_writer_t *self, bool value);
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 15927fc9fb31..693fc9710be1 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -95,5 +95,6 @@ int do_map(int argc, char **arg);
 int prog_parse_fd(int *argc, char ***argv);
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
+void print_hex_data_json(uint8_t *data, size_t len);
 
 #endif
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index f373f2baef5a..43e49799a624 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -385,7 +385,7 @@ static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
 	va_end(args);
 }
 
-static void dump_xlated(void *buf, unsigned int len, bool opcodes)
+static void dump_xlated_plain(void *buf, unsigned int len, bool opcodes)
 {
 	struct bpf_insn *insn = buf;
 	bool double_insn = false;
@@ -414,6 +414,69 @@ static void dump_xlated(void *buf, unsigned int len, bool opcodes)
 	}
 }
 
+static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...)
+{
+	unsigned int l = strlen(fmt);
+	char chomped_fmt[l];
+	va_list args;
+
+	va_start(args, fmt);
+	if (l > 0) {
+		strncpy(chomped_fmt, fmt, l - 1);
+		chomped_fmt[l - 1] = '\0';
+	}
+	jsonw_vprintf_enquote(json_wtr, chomped_fmt, args);
+	va_end(args);
+}
+
+static void dump_xlated_json(void *buf, unsigned int len, bool opcodes)
+{
+	struct bpf_insn *insn = buf;
+	bool double_insn = false;
+	unsigned int i;
+
+	jsonw_start_array(json_wtr);
+	for (i = 0; i < len / sizeof(*insn); i++) {
+		if (double_insn) {
+			double_insn = false;
+			continue;
+		}
+		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
+
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "disasm");
+		print_bpf_insn(print_insn_json, NULL, insn + i, true);
+
+		if (opcodes) {
+			jsonw_name(json_wtr, "opcodes");
+			jsonw_start_object(json_wtr);
+
+			jsonw_name(json_wtr, "code");
+			jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code);
+
+			jsonw_name(json_wtr, "src_reg");
+			jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg);
+
+			jsonw_name(json_wtr, "dst_reg");
+			jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg);
+
+			jsonw_name(json_wtr, "off");
+			print_hex_data_json((uint8_t *)(&insn[i].off), 2);
+
+			jsonw_name(json_wtr, "imm");
+			if (double_insn && i < len - 1)
+				print_hex_data_json((uint8_t *)(&insn[i].imm),
+						    12);
+			else
+				print_hex_data_json((uint8_t *)(&insn[i].imm),
+						    4);
+			jsonw_end_object(json_wtr);
+		}
+		jsonw_end_object(json_wtr);
+	}
+	jsonw_end_array(json_wtr);
+}
+
 static int do_dump(int argc, char **argv)
 {
 	struct bpf_prog_info info = {};
@@ -523,7 +586,10 @@ static int do_dump(int argc, char **argv)
 		if (member_len == &info.jited_prog_len)
 			disasm_print_insn(buf, *member_len, opcodes);
 		else
-			dump_xlated(buf, *member_len, opcodes);
+			if (json_output)
+				dump_xlated_json(buf, *member_len, opcodes);
+			else
+				dump_xlated_plain(buf, *member_len, opcodes);
 	}
 
 	free(buf);
-- 
cgit v1.2.3


From 831a0aafe5c39405150d47994fe0a5bcd78fbadc Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:11 -0700
Subject: tools: bpftool: add JSON output for `bpftool map *` commands

Reuse the json_writer API introduced in an earlier commit to make
bpftool able to generate JSON output on
`bpftool map { show | dump | lookup | getnext }` commands. Remaining
commands produce no output.

Some functions have been spit into plain-output and JSON versions in
order to remain readable.

Outputs for sample maps have been successfully tested against a JSON
validator.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/map.c | 149 +++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 129 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e1004d825392..14d89bfabc66 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -205,8 +205,45 @@ map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 	return fd;
 }
 
-static void print_entry(struct bpf_map_info *info, unsigned char *key,
-			unsigned char *value)
+static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
+			     unsigned char *value)
+{
+	jsonw_start_object(json_wtr);
+
+	if (!map_is_per_cpu(info->type)) {
+		jsonw_name(json_wtr, "key");
+		print_hex_data_json(key, info->key_size);
+		jsonw_name(json_wtr, "value");
+		print_hex_data_json(value, info->value_size);
+	} else {
+		unsigned int i, n;
+
+		n = get_possible_cpus();
+
+		jsonw_name(json_wtr, "key");
+		print_hex_data_json(key, info->key_size);
+
+		jsonw_name(json_wtr, "values");
+		jsonw_start_array(json_wtr);
+		for (i = 0; i < n; i++) {
+			jsonw_start_object(json_wtr);
+
+			jsonw_int_field(json_wtr, "cpu", i);
+
+			jsonw_name(json_wtr, "value");
+			print_hex_data_json(value + i * info->value_size,
+					    info->value_size);
+
+			jsonw_end_object(json_wtr);
+		}
+		jsonw_end_array(json_wtr);
+	}
+
+	jsonw_end_object(json_wtr);
+}
+
+static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
+			      unsigned char *value)
 {
 	if (!map_is_per_cpu(info->type)) {
 		bool single_line, break_names;
@@ -370,7 +407,41 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 	return -1;
 }
 
-static int show_map_close(int fd, struct bpf_map_info *info)
+static int show_map_close_json(int fd, struct bpf_map_info *info)
+{
+	char *memlock;
+
+	memlock = get_fdinfo(fd, "memlock");
+	close(fd);
+
+	jsonw_start_object(json_wtr);
+
+	jsonw_uint_field(json_wtr, "id", info->id);
+	if (info->type < ARRAY_SIZE(map_type_name))
+		jsonw_string_field(json_wtr, "type",
+				   map_type_name[info->type]);
+	else
+		jsonw_uint_field(json_wtr, "type", info->type);
+
+	if (*info->name)
+		jsonw_string_field(json_wtr, "name", info->name);
+
+	jsonw_name(json_wtr, "flags");
+	jsonw_printf(json_wtr, "%#x", info->map_flags);
+	jsonw_uint_field(json_wtr, "bytes_key", info->key_size);
+	jsonw_uint_field(json_wtr, "bytes_value", info->value_size);
+	jsonw_uint_field(json_wtr, "max_entries", info->max_entries);
+
+	if (memlock)
+		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+	free(memlock);
+
+	jsonw_end_object(json_wtr);
+
+	return 0;
+}
+
+static int show_map_close_plain(int fd, struct bpf_map_info *info)
 {
 	char *memlock;
 
@@ -412,12 +483,17 @@ static int do_show(int argc, char **argv)
 		if (fd < 0)
 			return -1;
 
-		return show_map_close(fd, &info);
+		if (json_output)
+			return show_map_close_json(fd, &info);
+		else
+			return show_map_close_plain(fd, &info);
 	}
 
 	if (argc)
 		return BAD_ARG();
 
+	if (json_output)
+		jsonw_start_array(json_wtr);
 	while (true) {
 		err = bpf_map_get_next_id(id, &id);
 		if (err) {
@@ -443,8 +519,13 @@ static int do_show(int argc, char **argv)
 			return -1;
 		}
 
-		show_map_close(fd, &info);
+		if (json_output)
+			show_map_close_json(fd, &info);
+		else
+			show_map_close_plain(fd, &info);
 	}
+	if (json_output)
+		jsonw_end_array(json_wtr);
 
 	return errno == ENOENT ? 0 : -1;
 }
@@ -480,6 +561,8 @@ static int do_dump(int argc, char **argv)
 	}
 
 	prev_key = NULL;
+	if (json_output)
+		jsonw_start_array(json_wtr);
 	while (true) {
 		err = bpf_map_get_next_key(fd, prev_key, key);
 		if (err) {
@@ -489,7 +572,10 @@ static int do_dump(int argc, char **argv)
 		}
 
 		if (!bpf_map_lookup_elem(fd, key, value)) {
-			print_entry(&info, key, value);
+			if (json_output)
+				print_entry_json(&info, key, value);
+			else
+				print_entry_plain(&info, key, value);
 		} else {
 			info("can't lookup element with key: ");
 			fprint_hex(stderr, key, info.key_size, " ");
@@ -500,7 +586,11 @@ static int do_dump(int argc, char **argv)
 		num_elems++;
 	}
 
-	printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : "");
+	if (json_output)
+		jsonw_end_array(json_wtr);
+	else
+		printf("Found %u element%s\n", num_elems,
+		       num_elems != 1 ? "s" : "");
 
 exit_free:
 	free(key);
@@ -584,11 +674,18 @@ static int do_lookup(int argc, char **argv)
 
 	err = bpf_map_lookup_elem(fd, key, value);
 	if (!err) {
-		print_entry(&info, key, value);
+		if (json_output)
+			print_entry_json(&info, key, value);
+		else
+			print_entry_plain(&info, key, value);
 	} else if (errno == ENOENT) {
-		printf("key:\n");
-		fprint_hex(stdout, key, info.key_size, " ");
-		printf("\n\nNot found\n");
+		if (json_output) {
+			jsonw_null(json_wtr);
+		} else {
+			printf("key:\n");
+			fprint_hex(stdout, key, info.key_size, " ");
+			printf("\n\nNot found\n");
+		}
 	} else {
 		err("lookup failed: %s\n", strerror(errno));
 	}
@@ -640,18 +737,30 @@ static int do_getnext(int argc, char **argv)
 		goto exit_free;
 	}
 
-	if (key) {
-		printf("key:\n");
-		fprint_hex(stdout, key, info.key_size, " ");
-		printf("\n");
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		if (key) {
+			jsonw_name(json_wtr, "key");
+			print_hex_data_json(key, info.key_size);
+		} else {
+			jsonw_null_field(json_wtr, "key");
+		}
+		jsonw_name(json_wtr, "next_key");
+		print_hex_data_json(nextkey, info.key_size);
+		jsonw_end_object(json_wtr);
 	} else {
-		printf("key: None\n");
+		if (key) {
+			printf("key:\n");
+			fprint_hex(stdout, key, info.key_size, " ");
+			printf("\n");
+		} else {
+			printf("key: None\n");
+		}
+		printf("next key:\n");
+		fprint_hex(stdout, nextkey, info.key_size, " ");
+		printf("\n");
 	}
 
-	printf("next key:\n");
-	fprint_hex(stdout, nextkey, info.key_size, " ");
-	printf("\n");
-
 exit_free:
 	free(nextkey);
 	free(key);
-- 
cgit v1.2.3


From 3aaca6bf7a09150e4c87f2932dc8ebe82a586252 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:12 -0700
Subject: tools: bpftool: add JSON output for `bpftool batch file FILE` command

`bpftool batch file FILE` takes FILE as an argument and executes all the
bpftool commands it finds inside (or stops if an error occurs).

To obtain a consistent JSON output, create a root JSON array, then for
each command create a new object containing two fields: one with the
command arguments, the other with the output (which is the JSON object
that the command would have produced, if called on its own).

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/main.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 14bfc17cd4de..71b01bf73912 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -155,6 +155,7 @@ static int do_batch(int argc, char **argv)
 	int n_argc;
 	FILE *fp;
 	int err;
+	int i;
 
 	if (argc < 2) {
 		err("too few parameters for batch\n");
@@ -174,6 +175,8 @@ static int do_batch(int argc, char **argv)
 		return -1;
 	}
 
+	if (json_output)
+		jsonw_start_array(json_wtr);
 	while (fgets(buf, sizeof(buf), fp)) {
 		if (strlen(buf) == sizeof(buf) - 1) {
 			errno = E2BIG;
@@ -197,7 +200,21 @@ static int do_batch(int argc, char **argv)
 		if (!n_argc)
 			continue;
 
+		if (json_output) {
+			jsonw_start_object(json_wtr);
+			jsonw_name(json_wtr, "command");
+			jsonw_start_array(json_wtr);
+			for (i = 0; i < n_argc; i++)
+				jsonw_string(json_wtr, n_argv[i]);
+			jsonw_end_array(json_wtr);
+			jsonw_name(json_wtr, "output");
+		}
+
 		err = cmd_select(cmds, n_argc, n_argv, do_help);
+
+		if (json_output)
+			jsonw_end_object(json_wtr);
+
 		if (err)
 			goto err_close;
 
@@ -214,6 +231,9 @@ static int do_batch(int argc, char **argv)
 err_close:
 	fclose(fp);
 
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 9a5ab8bf1d6d16ef47fdf55dba1683ec00d751ad Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:13 -0700
Subject: tools: bpftool: turn err() and info() macros into functions

Turn err() and info() macros into functions.

In order to avoid naming conflicts with variables in the code, rename
them as p_err() and p_info() respectively.

The behavior of these functions is similar to the one of the macros for
plain output. However, when JSON output is requested, these macros
return a JSON-formatted "error" object instead of printing a message to
stderr.

To handle error messages correctly with JSON, a modification was brought
to their behavior nonetheless: the functions now append a end-of-line
character at the end of the message. This way, we can remove end-of-line
characters at the end of the argument strings, and not have them in the
JSON output.

All error messages are formatted to hold in a single call to p_err(), in
order to produce a single JSON field.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/common.c | 26 +++++++-------
 tools/bpf/bpftool/main.c   | 16 ++++-----
 tools/bpf/bpftool/main.h   | 37 +++++++++++++++++---
 tools/bpf/bpftool/map.c    | 87 +++++++++++++++++++++++++---------------------
 tools/bpf/bpftool/prog.c   | 51 +++++++++++++--------------
 5 files changed, 126 insertions(+), 91 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index e7a756b8ee21..b2533f1cae3e 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -66,8 +66,8 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 
 	fd = bpf_obj_get(path);
 	if (fd < 0) {
-		err("bpf obj get (%s): %s\n", path,
-		    errno == EACCES && !is_bpffs(dirname(path)) ?
+		p_err("bpf obj get (%s): %s", path,
+		      errno == EACCES && !is_bpffs(dirname(path)) ?
 		    "directory not in bpf file system (bpffs)" :
 		    strerror(errno));
 		return -1;
@@ -79,7 +79,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 		return type;
 	}
 	if (type != exp_type) {
-		err("incorrect object type: %s\n", get_fd_type_name(type));
+		p_err("incorrect object type: %s", get_fd_type_name(type));
 		close(fd);
 		return -1;
 	}
@@ -95,14 +95,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	int fd;
 
 	if (!is_prefix(*argv, "id")) {
-		err("expected 'id' got %s\n", *argv);
+		p_err("expected 'id' got %s", *argv);
 		return -1;
 	}
 	NEXT_ARG();
 
 	id = strtoul(*argv, &endptr, 0);
 	if (*endptr) {
-		err("can't parse %s as ID\n", *argv);
+		p_err("can't parse %s as ID", *argv);
 		return -1;
 	}
 	NEXT_ARG();
@@ -112,15 +112,15 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 
 	fd = get_fd_by_id(id);
 	if (fd < 0) {
-		err("can't get prog by id (%u): %s\n", id, strerror(errno));
+		p_err("can't get prog by id (%u): %s", id, strerror(errno));
 		return -1;
 	}
 
 	err = bpf_obj_pin(fd, *argv);
 	close(fd);
 	if (err) {
-		err("can't pin the object (%s): %s\n", *argv,
-		    errno == EACCES && !is_bpffs(dirname(*argv)) ?
+		p_err("can't pin the object (%s): %s", *argv,
+		      errno == EACCES && !is_bpffs(dirname(*argv)) ?
 		    "directory not in bpf file system (bpffs)" :
 		    strerror(errno));
 		return -1;
@@ -153,11 +153,11 @@ int get_fd_type(int fd)
 
 	n = readlink(path, buf, sizeof(buf));
 	if (n < 0) {
-		err("can't read link type: %s\n", strerror(errno));
+		p_err("can't read link type: %s", strerror(errno));
 		return -1;
 	}
 	if (n == sizeof(path)) {
-		err("can't read link type: path too long!\n");
+		p_err("can't read link type: path too long!");
 		return -1;
 	}
 
@@ -181,7 +181,7 @@ char *get_fdinfo(int fd, const char *key)
 
 	fdi = fopen(path, "r");
 	if (!fdi) {
-		err("can't open fdinfo: %s\n", strerror(errno));
+		p_err("can't open fdinfo: %s", strerror(errno));
 		return NULL;
 	}
 
@@ -196,7 +196,7 @@ char *get_fdinfo(int fd, const char *key)
 
 		value = strchr(line, '\t');
 		if (!value || !value[1]) {
-			err("malformed fdinfo!?\n");
+			p_err("malformed fdinfo!?");
 			free(line);
 			return NULL;
 		}
@@ -209,7 +209,7 @@ char *get_fdinfo(int fd, const char *key)
 		return line;
 	}
 
-	err("key '%s' not found in fdinfo\n", key);
+	p_err("key '%s' not found in fdinfo", key);
 	free(line);
 	fclose(fdi);
 	return NULL;
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 71b01bf73912..9989a77fdc4a 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -158,20 +158,20 @@ static int do_batch(int argc, char **argv)
 	int i;
 
 	if (argc < 2) {
-		err("too few parameters for batch\n");
+		p_err("too few parameters for batch");
 		return -1;
 	} else if (!is_prefix(*argv, "file")) {
-		err("expected 'file', got: %s\n", *argv);
+		p_err("expected 'file', got: %s", *argv);
 		return -1;
 	} else if (argc > 2) {
-		err("too many parameters for batch\n");
+		p_err("too many parameters for batch");
 		return -1;
 	}
 	NEXT_ARG();
 
 	fp = fopen(*argv, "r");
 	if (!fp) {
-		err("Can't open file (%s): %s\n", *argv, strerror(errno));
+		p_err("Can't open file (%s): %s", *argv, strerror(errno));
 		return -1;
 	}
 
@@ -189,8 +189,8 @@ static int do_batch(int argc, char **argv)
 		while (n_argv[n_argc]) {
 			n_argc++;
 			if (n_argc == ARRAY_SIZE(n_argv)) {
-				err("line %d has too many arguments, skip\n",
-				    lines);
+				p_err("line %d has too many arguments, skip",
+				      lines);
 				n_argc = 0;
 				break;
 			}
@@ -225,7 +225,7 @@ static int do_batch(int argc, char **argv)
 		perror("reading batch file failed");
 		err = -1;
 	} else {
-		info("processed %d lines\n", lines);
+		p_info("processed %d lines", lines);
 		err = 0;
 	}
 err_close:
@@ -279,7 +279,7 @@ int main(int argc, char **argv)
 	if (json_output) {
 		json_wtr = jsonw_new(stdout);
 		if (!json_wtr) {
-			err("failed to create JSON writer\n");
+			p_err("failed to create JSON writer");
 			return -1;
 		}
 		jsonw_pretty(json_wtr, pretty_output);
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 693fc9710be1..04c88b55d8c7 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -45,15 +45,11 @@
 
 #include "json_writer.h"
 
-#define err(msg...)	fprintf(stderr, "Error: " msg)
-#define warn(msg...)	fprintf(stderr, "Warning: " msg)
-#define info(msg...)	fprintf(stderr, msg)
-
 #define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
 
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
-#define BAD_ARG()	({ err("what is '%s'?\n", *argv); -1; })
+#define BAD_ARG()	({ p_err("what is '%s'?\n", *argv); -1; })
 
 #define BPF_TAG_FMT	"%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
 
@@ -97,4 +93,35 @@ int prog_parse_fd(int *argc, char ***argv);
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
 void print_hex_data_json(uint8_t *data, size_t len);
 
+static inline void p_err(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "error");
+		jsonw_vprintf_enquote(json_wtr, fmt, ap);
+		jsonw_end_object(json_wtr);
+	} else {
+		fprintf(stderr, "Error: ");
+		vfprintf(stderr, fmt, ap);
+		fprintf(stderr, "\n");
+	}
+	va_end(ap);
+}
+
+static inline void p_info(const char *fmt, ...)
+{
+	va_list ap;
+
+	if (json_output)
+		return;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	fprintf(stderr, "\n");
+	va_end(ap);
+}
+
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 14d89bfabc66..86c128c433ba 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -81,19 +81,19 @@ static unsigned int get_possible_cpus(void)
 
 	fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
 	if (fd < 0) {
-		err("can't open sysfs possible cpus\n");
+		p_err("can't open sysfs possible cpus");
 		exit(-1);
 	}
 
 	n = read(fd, buf, sizeof(buf));
 	if (n < 2) {
-		err("can't read sysfs possible cpus\n");
+		p_err("can't read sysfs possible cpus");
 		exit(-1);
 	}
 	close(fd);
 
 	if (n == sizeof(buf)) {
-		err("read sysfs possible cpus overflow\n");
+		p_err("read sysfs possible cpus overflow");
 		exit(-1);
 	}
 
@@ -161,14 +161,14 @@ static int map_parse_fd(int *argc, char ***argv)
 
 		id = strtoul(**argv, &endptr, 0);
 		if (*endptr) {
-			err("can't parse %s as ID\n", **argv);
+			p_err("can't parse %s as ID", **argv);
 			return -1;
 		}
 		NEXT_ARGP();
 
 		fd = bpf_map_get_fd_by_id(id);
 		if (fd < 0)
-			err("get map by id (%u): %s\n", id, strerror(errno));
+			p_err("get map by id (%u): %s", id, strerror(errno));
 		return fd;
 	} else if (is_prefix(**argv, "pinned")) {
 		char *path;
@@ -181,7 +181,7 @@ static int map_parse_fd(int *argc, char ***argv)
 		return open_obj_pinned_any(path, BPF_OBJ_MAP);
 	}
 
-	err("expected 'id' or 'pinned', got: '%s'?\n", **argv);
+	p_err("expected 'id' or 'pinned', got: '%s'?", **argv);
 	return -1;
 }
 
@@ -197,7 +197,7 @@ map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 
 	err = bpf_obj_get_info_by_fd(fd, info, info_len);
 	if (err) {
-		err("can't get map info: %s\n", strerror(errno));
+		p_err("can't get map info: %s", strerror(errno));
 		close(fd);
 		return err;
 	}
@@ -288,14 +288,14 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val,
 	while (i < n && argv[i]) {
 		val[i] = strtoul(argv[i], &endptr, 0);
 		if (*endptr) {
-			err("error parsing byte: %s\n", argv[i]);
+			p_err("error parsing byte: %s", argv[i]);
 			return NULL;
 		}
 		i++;
 	}
 
 	if (i != n) {
-		err("%s expected %d bytes got %d\n", name, n, i);
+		p_err("%s expected %d bytes got %d", name, n, i);
 		return NULL;
 	}
 
@@ -309,16 +309,16 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 	if (!*argv) {
 		if (!key && !value)
 			return 0;
-		err("did not find %s\n", key ? "key" : "value");
+		p_err("did not find %s", key ? "key" : "value");
 		return -1;
 	}
 
 	if (is_prefix(*argv, "key")) {
 		if (!key) {
 			if (key_size)
-				err("duplicate key\n");
+				p_err("duplicate key");
 			else
-				err("unnecessary key\n");
+				p_err("unnecessary key");
 			return -1;
 		}
 
@@ -333,9 +333,9 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 
 		if (!value) {
 			if (value_size)
-				err("duplicate value\n");
+				p_err("duplicate value");
 			else
-				err("unnecessary value\n");
+				p_err("unnecessary value");
 			return -1;
 		}
 
@@ -345,11 +345,11 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 			int argc = 2;
 
 			if (value_size != 4) {
-				err("value smaller than 4B for map in map?\n");
+				p_err("value smaller than 4B for map in map?");
 				return -1;
 			}
 			if (!argv[0] || !argv[1]) {
-				err("not enough value arguments for map in map\n");
+				p_err("not enough value arguments for map in map");
 				return -1;
 			}
 
@@ -363,11 +363,11 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 			int argc = 2;
 
 			if (value_size != 4) {
-				err("value smaller than 4B for map of progs?\n");
+				p_err("value smaller than 4B for map of progs?");
 				return -1;
 			}
 			if (!argv[0] || !argv[1]) {
-				err("not enough value arguments for map of progs\n");
+				p_err("not enough value arguments for map of progs");
 				return -1;
 			}
 
@@ -388,7 +388,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 	} else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") ||
 		   is_prefix(*argv, "exist")) {
 		if (!flags) {
-			err("flags specified multiple times: %s\n", *argv);
+			p_err("flags specified multiple times: %s", *argv);
 			return -1;
 		}
 
@@ -403,7 +403,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 				  value_size, NULL, value_fd);
 	}
 
-	err("expected key or value, got: %s\n", *argv);
+	p_err("expected key or value, got: %s", *argv);
 	return -1;
 }
 
@@ -499,22 +499,21 @@ static int do_show(int argc, char **argv)
 		if (err) {
 			if (errno == ENOENT)
 				break;
-			err("can't get next map: %s\n", strerror(errno));
-			if (errno == EINVAL)
-				err("kernel too old?\n");
+			p_err("can't get next map: %s%s", strerror(errno),
+			      errno == EINVAL ? " -- kernel too old?" : "");
 			return -1;
 		}
 
 		fd = bpf_map_get_fd_by_id(id);
 		if (fd < 0) {
-			err("can't get map by id (%u): %s\n",
-			    id, strerror(errno));
+			p_err("can't get map by id (%u): %s",
+			      id, strerror(errno));
 			return -1;
 		}
 
 		err = bpf_obj_get_info_by_fd(fd, &info, &len);
 		if (err) {
-			err("can't get map info: %s\n", strerror(errno));
+			p_err("can't get map info: %s", strerror(errno));
 			close(fd);
 			return -1;
 		}
@@ -547,7 +546,7 @@ static int do_dump(int argc, char **argv)
 		return -1;
 
 	if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
-		err("Dumping maps of maps and program maps not supported\n");
+		p_err("Dumping maps of maps and program maps not supported");
 		close(fd);
 		return -1;
 	}
@@ -555,7 +554,7 @@ static int do_dump(int argc, char **argv)
 	key = malloc(info.key_size);
 	value = alloc_value(&info);
 	if (!key || !value) {
-		err("mem alloc failed\n");
+		p_err("mem alloc failed");
 		err = -1;
 		goto exit_free;
 	}
@@ -577,9 +576,19 @@ static int do_dump(int argc, char **argv)
 			else
 				print_entry_plain(&info, key, value);
 		} else {
-			info("can't lookup element with key: ");
-			fprint_hex(stderr, key, info.key_size, " ");
-			fprintf(stderr, "\n");
+			if (json_output) {
+				jsonw_name(json_wtr, "key");
+				print_hex_data_json(key, info.key_size);
+				jsonw_name(json_wtr, "value");
+				jsonw_start_object(json_wtr);
+				jsonw_string_field(json_wtr, "error",
+						   "can't lookup element");
+				jsonw_end_object(json_wtr);
+			} else {
+				p_info("can't lookup element with key: ");
+				fprint_hex(stderr, key, info.key_size, " ");
+				fprintf(stderr, "\n");
+			}
 		}
 
 		prev_key = key;
@@ -619,7 +628,7 @@ static int do_update(int argc, char **argv)
 	key = malloc(info.key_size);
 	value = alloc_value(&info);
 	if (!key || !value) {
-		err("mem alloc failed");
+		p_err("mem alloc failed");
 		err = -1;
 		goto exit_free;
 	}
@@ -631,7 +640,7 @@ static int do_update(int argc, char **argv)
 
 	err = bpf_map_update_elem(fd, key, value, flags);
 	if (err) {
-		err("update failed: %s\n", strerror(errno));
+		p_err("update failed: %s", strerror(errno));
 		goto exit_free;
 	}
 
@@ -663,7 +672,7 @@ static int do_lookup(int argc, char **argv)
 	key = malloc(info.key_size);
 	value = alloc_value(&info);
 	if (!key || !value) {
-		err("mem alloc failed");
+		p_err("mem alloc failed");
 		err = -1;
 		goto exit_free;
 	}
@@ -687,7 +696,7 @@ static int do_lookup(int argc, char **argv)
 			printf("\n\nNot found\n");
 		}
 	} else {
-		err("lookup failed: %s\n", strerror(errno));
+		p_err("lookup failed: %s", strerror(errno));
 	}
 
 exit_free:
@@ -716,7 +725,7 @@ static int do_getnext(int argc, char **argv)
 	key = malloc(info.key_size);
 	nextkey = malloc(info.key_size);
 	if (!key || !nextkey) {
-		err("mem alloc failed");
+		p_err("mem alloc failed");
 		err = -1;
 		goto exit_free;
 	}
@@ -733,7 +742,7 @@ static int do_getnext(int argc, char **argv)
 
 	err = bpf_map_get_next_key(fd, key, nextkey);
 	if (err) {
-		err("can't get next key: %s\n", strerror(errno));
+		p_err("can't get next key: %s", strerror(errno));
 		goto exit_free;
 	}
 
@@ -786,7 +795,7 @@ static int do_delete(int argc, char **argv)
 
 	key = malloc(info.key_size);
 	if (!key) {
-		err("mem alloc failed");
+		p_err("mem alloc failed");
 		err = -1;
 		goto exit_free;
 	}
@@ -797,7 +806,7 @@ static int do_delete(int argc, char **argv)
 
 	err = bpf_map_delete_elem(fd, key);
 	if (err)
-		err("delete failed: %s\n", strerror(errno));
+		p_err("delete failed: %s", strerror(errno));
 
 exit_free:
 	free(key);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 43e49799a624..41bd5390b4fc 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -104,21 +104,21 @@ static int prog_fd_by_tag(unsigned char *tag)
 	while (true) {
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
-			err("%s\n", strerror(errno));
+			p_err("%s", strerror(errno));
 			return -1;
 		}
 
 		fd = bpf_prog_get_fd_by_id(id);
 		if (fd < 0) {
-			err("can't get prog by id (%u): %s\n",
-			    id, strerror(errno));
+			p_err("can't get prog by id (%u): %s",
+			      id, strerror(errno));
 			return -1;
 		}
 
 		err = bpf_obj_get_info_by_fd(fd, &info, &len);
 		if (err) {
-			err("can't get prog info (%u): %s\n",
-			    id, strerror(errno));
+			p_err("can't get prog info (%u): %s",
+			      id, strerror(errno));
 			close(fd);
 			return -1;
 		}
@@ -142,14 +142,14 @@ int prog_parse_fd(int *argc, char ***argv)
 
 		id = strtoul(**argv, &endptr, 0);
 		if (*endptr) {
-			err("can't parse %s as ID\n", **argv);
+			p_err("can't parse %s as ID", **argv);
 			return -1;
 		}
 		NEXT_ARGP();
 
 		fd = bpf_prog_get_fd_by_id(id);
 		if (fd < 0)
-			err("get by id (%u): %s\n", id, strerror(errno));
+			p_err("get by id (%u): %s", id, strerror(errno));
 		return fd;
 	} else if (is_prefix(**argv, "tag")) {
 		unsigned char tag[BPF_TAG_SIZE];
@@ -159,7 +159,7 @@ int prog_parse_fd(int *argc, char ***argv)
 		if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
 			   tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
 		    != BPF_TAG_SIZE) {
-			err("can't parse tag\n");
+			p_err("can't parse tag");
 			return -1;
 		}
 		NEXT_ARGP();
@@ -176,7 +176,7 @@ int prog_parse_fd(int *argc, char ***argv)
 		return open_obj_pinned_any(path, BPF_OBJ_PROG);
 	}
 
-	err("expected 'id', 'tag' or 'pinned', got: '%s'?\n", **argv);
+	p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv);
 	return -1;
 }
 
@@ -311,7 +311,7 @@ static int show_prog(int fd)
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	if (err) {
-		err("can't get prog info: %s\n", strerror(errno));
+		p_err("can't get prog info: %s", strerror(errno));
 		return -1;
 	}
 
@@ -349,17 +349,16 @@ static int do_show(int argc, char **argv)
 				err = 0;
 				break;
 			}
-			err("can't get next program: %s\n", strerror(errno));
-			if (errno == EINVAL)
-				err("kernel too old?\n");
+			p_err("can't get next program: %s%s", strerror(errno),
+			      errno == EINVAL ? " -- kernel too old?" : "");
 			err = -1;
 			break;
 		}
 
 		fd = bpf_prog_get_fd_by_id(id);
 		if (fd < 0) {
-			err("can't get prog by id (%u): %s\n",
-			    id, strerror(errno));
+			p_err("can't get prog by id (%u): %s",
+			      id, strerror(errno));
 			err = -1;
 			break;
 		}
@@ -498,7 +497,7 @@ static int do_dump(int argc, char **argv)
 		member_len = &info.xlated_prog_len;
 		member_ptr = &info.xlated_prog_insns;
 	} else {
-		err("expected 'xlated' or 'jited', got: %s\n", *argv);
+		p_err("expected 'xlated' or 'jited', got: %s", *argv);
 		return -1;
 	}
 	NEXT_ARG();
@@ -513,7 +512,7 @@ static int do_dump(int argc, char **argv)
 	if (is_prefix(*argv, "file")) {
 		NEXT_ARG();
 		if (!argc) {
-			err("expected file path\n");
+			p_err("expected file path");
 			return -1;
 		}
 
@@ -531,12 +530,12 @@ static int do_dump(int argc, char **argv)
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	if (err) {
-		err("can't get prog info: %s\n", strerror(errno));
+		p_err("can't get prog info: %s", strerror(errno));
 		return -1;
 	}
 
 	if (!*member_len) {
-		info("no instructions returned\n");
+		p_info("no instructions returned");
 		close(fd);
 		return 0;
 	}
@@ -545,7 +544,7 @@ static int do_dump(int argc, char **argv)
 
 	buf = malloc(buf_size);
 	if (!buf) {
-		err("mem alloc failed\n");
+		p_err("mem alloc failed");
 		close(fd);
 		return -1;
 	}
@@ -558,28 +557,28 @@ static int do_dump(int argc, char **argv)
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	close(fd);
 	if (err) {
-		err("can't get prog info: %s\n", strerror(errno));
+		p_err("can't get prog info: %s", strerror(errno));
 		goto err_free;
 	}
 
 	if (*member_len > buf_size) {
-		err("too many instructions returned\n");
+		p_err("too many instructions returned");
 		goto err_free;
 	}
 
 	if (filepath) {
 		fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
 		if (fd < 0) {
-			err("can't open file %s: %s\n", filepath,
-			    strerror(errno));
+			p_err("can't open file %s: %s", filepath,
+			      strerror(errno));
 			goto err_free;
 		}
 
 		n = write(fd, buf, *member_len);
 		close(fd);
 		if (n != *member_len) {
-			err("error writing output file: %s\n",
-			    n < 0 ? strerror(errno) : "short write");
+			p_err("error writing output file: %s",
+			      n < 0 ? strerror(errno) : "short write");
 			goto err_free;
 		}
 	} else {
-- 
cgit v1.2.3


From 004b45c0e51a8b6f20320181a946ba2d1bd3548b Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:14 -0700
Subject: tools: bpftool: provide JSON output for all possible commands

As all commands can now return JSON output (possibly just a "null"
value), output of `bpftool --json batch file FILE` should also be fully
JSON compliant.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/main.c | 25 +++++++++++++++++++++----
 tools/bpf/bpftool/map.c  | 16 +++++++++++++++-
 tools/bpf/bpftool/prog.c | 12 +++++++++++-
 3 files changed, 47 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 9989a77fdc4a..55ba0a04c102 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -64,6 +64,11 @@ void usage(void)
 
 static int do_help(int argc, char **argv)
 {
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
 	fprintf(stderr,
 		"Usage: %s OBJECT { COMMAND | help }\n"
 		"       %s batch file FILE\n"
@@ -77,10 +82,22 @@ static int do_help(int argc, char **argv)
 
 static int do_version(int argc, char **argv)
 {
-	printf("%s v%d.%d.%d\n", bin_name,
-	       LINUX_VERSION_CODE >> 16,
-	       LINUX_VERSION_CODE >> 8 & 0xf,
-	       LINUX_VERSION_CODE & 0xf);
+	unsigned int version[3];
+
+	version[0] = LINUX_VERSION_CODE >> 16;
+	version[1] = LINUX_VERSION_CODE >> 8 & 0xf;
+	version[2] = LINUX_VERSION_CODE & 0xf;
+
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "version");
+		jsonw_printf(json_wtr, "\"%u.%u.%u\"",
+			     version[0], version[1], version[2]);
+		jsonw_end_object(json_wtr);
+	} else {
+		printf("%s v%u.%u.%u\n", bin_name,
+		       version[0], version[1], version[2]);
+	}
 	return 0;
 }
 
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 86c128c433ba..a611f31f574f 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -651,6 +651,8 @@ exit_free:
 	free(value);
 	close(fd);
 
+	if (!err && json_output)
+		jsonw_null(json_wtr);
 	return err;
 }
 
@@ -812,16 +814,28 @@ exit_free:
 	free(key);
 	close(fd);
 
+	if (!err && json_output)
+		jsonw_null(json_wtr);
 	return err;
 }
 
 static int do_pin(int argc, char **argv)
 {
-	return do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+	int err;
+
+	err = do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+	if (!err && json_output)
+		jsonw_null(json_wtr);
+	return err;
 }
 
 static int do_help(int argc, char **argv)
 {
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
 	fprintf(stderr,
 		"Usage: %s %s show   [MAP]\n"
 		"       %s %s dump    MAP\n"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 41bd5390b4fc..e07f35ff80d1 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -602,11 +602,21 @@ err_free:
 
 static int do_pin(int argc, char **argv)
 {
-	return do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+	int err;
+
+	err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+	if (!err && json_output)
+		jsonw_null(json_wtr);
+	return err;
 }
 
 static int do_help(int argc, char **argv)
 {
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
 	fprintf(stderr,
 		"Usage: %s %s show [PROG]\n"
 		"       %s %s dump xlated PROG [{ file FILE | opcodes }]\n"
-- 
cgit v1.2.3


From 47ff7ac6d706c6f08153294c87287aeec183b211 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:15 -0700
Subject: tools: bpftool: add cosmetic changes for the manual pages

Make the look-and-feel of the manual pages somewhat closer to other
manual pages, such as the ones from the utilities from iproute2, by
highlighting more keywords.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst  | 25 ++++++++++++------------
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 12 ++++++------
 tools/bpf/bpftool/Documentation/bpftool.rst      | 12 +++++++-----
 3 files changed, 26 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 5210c4fab356..3954b3ea4f26 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -13,23 +13,24 @@ SYNOPSIS
 	**bpftool** **map** *COMMAND*
 
 	*COMMANDS* :=
-	{ show | dump | update | lookup | getnext | delete | pin | help }
+	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
+	| **pin** | **help** }
 
 MAP COMMANDS
 =============
 
-|	**bpftool** map show   [*MAP*]
-|	**bpftool** map dump    *MAP*
-|	**bpftool** map update  *MAP*  key *BYTES*   value *VALUE* [*UPDATE_FLAGS*]
-|	**bpftool** map lookup  *MAP*  key *BYTES*
-|	**bpftool** map getnext *MAP* [key *BYTES*]
-|	**bpftool** map delete  *MAP*  key *BYTES*
-|	**bpftool** map pin     *MAP*  *FILE*
-|	**bpftool** map help
+|	**bpftool** **map show**   [*MAP*]
+|	**bpftool** **map dump**    *MAP*
+|	**bpftool** **map update**  *MAP*  **key** *BYTES*   **value** *VALUE* [*UPDATE_FLAGS*]
+|	**bpftool** **map lookup**  *MAP*  **key** *BYTES*
+|	**bpftool** **map getnext** *MAP* [**key** *BYTES*]
+|	**bpftool** **map delete**  *MAP*  **key** *BYTES*
+|	**bpftool** **map pin**     *MAP*  *FILE*
+|	**bpftool** **map help**
 |
-|	*MAP* := { id MAP_ID | pinned FILE }
-|	*VALUE* := { BYTES | MAP | PROGRAM }
-|	*UPDATE_FLAGS* := { any | exist | noexist }
+|	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
+|	*VALUE* := { *BYTES* | *MAP* | *PROGRAM* }
+|	*UPDATE_FLAGS* := { **any** | **exist** | **noexist** }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 6620a81d9dc9..685a19e71fec 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -10,13 +10,13 @@ tool for inspection and simple manipulation of eBPF progs
 SYNOPSIS
 ========
 
-|	**bpftool** prog show [*PROG*]
-|	**bpftool** prog dump xlated *PROG* [{file *FILE* | opcodes }]
-|	**bpftool** prog dump jited  *PROG* [{file *FILE* | opcodes }]
-|	**bpftool** prog pin *PROG* *FILE*
-|	**bpftool** prog help
+|	**bpftool** **prog show** [*PROG*]
+|	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes**}]
+|	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
+|	**bpftool** **prog pin** *PROG* *FILE*
+|	**bpftool** **prog help**
 |
-|	*PROG* := { id *PROG_ID* | pinned *FILE* | tag *PROG_TAG* }
+|	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 9c04cd6677bd..44e07799d54d 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -10,18 +10,20 @@ tool for inspection and simple manipulation of eBPF programs and maps
 SYNOPSIS
 ========
 
-	**bpftool** *OBJECT* { *COMMAND* | help }
+	**bpftool** *OBJECT* { *COMMAND* | **help** }
 
-	**bpftool** batch file *FILE*
+	**bpftool** **batch file** *FILE*
 
-	**bpftool** version
+	**bpftool** **version**
 
 	*OBJECT* := { **map** | **program** }
 
 	*MAP-COMMANDS* :=
-	{ show | dump | update | lookup | getnext | delete | pin | help }
+	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
+	| **pin** | **help** }
 
-	*PROG-COMMANDS* := { show | dump jited | dump xlated | pin | help }
+	*PROG-COMMANDS* := { **show** | **dump jited** | **dump xlated** | **pin**
+	| **help** }
 
 DESCRIPTION
 ===========
-- 
cgit v1.2.3


From 0641c3c890d480abeb237b92a5ee4b99a22319c6 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 23 Oct 2017 09:24:16 -0700
Subject: tools: bpftool: update documentation for --json and --pretty usage

Update the documentation to provide help about JSON output generation,
and add an example in bpftool-prog manual page.

Also reintroduce an example that was left aside when the tool was moved
from GitHub to the kernel sources, in order to show how to mount the
bpffs file system (to pin programs) inside the bpftool-prog manual page.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst  | 11 ++++-
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 61 +++++++++++++++++++++++-
 tools/bpf/bpftool/Documentation/bpftool.rst      | 12 ++++-
 tools/bpf/bpftool/main.c                         |  6 ++-
 tools/bpf/bpftool/main.h                         |  2 +
 tools/bpf/bpftool/map.c                          |  1 +
 tools/bpf/bpftool/prog.c                         |  1 +
 7 files changed, 88 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 3954b3ea4f26..abb9ee940b15 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -10,7 +10,9 @@ tool for inspection and simple manipulation of eBPF maps
 SYNOPSIS
 ========
 
-	**bpftool** **map** *COMMAND*
+	**bpftool** [*OPTIONS*] **map** *COMMAND*
+
+	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
 
 	*COMMANDS* :=
 	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
@@ -77,6 +79,13 @@ OPTIONS
 	-v, --version
 		  Print version number (similar to **bpftool version**).
 
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
 EXAMPLES
 ========
 **# bpftool map show**
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 685a19e71fec..0f25d3c39e05 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -10,6 +10,16 @@ tool for inspection and simple manipulation of eBPF progs
 SYNOPSIS
 ========
 
+	**bpftool** [*OPTIONS*] **prog** *COMMAND*
+
+	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+	*COMMANDS* :=
+	{ **show** | **dump xlated** | **dump jited** | **pin** | **help** }
+
+MAP COMMANDS
+=============
+
 |	**bpftool** **prog show** [*PROG*]
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
@@ -58,6 +68,13 @@ OPTIONS
 	-v, --version
 		  Print version number (similar to **bpftool version**).
 
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
 EXAMPLES
 ========
 **# bpftool prog show**
@@ -67,13 +84,33 @@ EXAMPLES
 	loaded_at Sep 29/20:11  uid 0
 	xlated 528B  jited 370B  memlock 4096B  map_ids 10
 
+**# bpftool --json --pretty prog show**
+
+::
+
+    {
+        "programs": [{
+                "id": 10,
+                "type": "xdp",
+                "tag": "005a3d2123620c8b",
+                "loaded_at": "Sep 29/20:11",
+                "uid": 0,
+                "bytes_xlated": 528,
+                "jited": true,
+                "bytes_jited": 370,
+                "bytes_memlock": 4096,
+                "map_ids": [10
+                ]
+            }
+        ]
+    }
+
 |
 | **# bpftool prog dump xlated id 10 file /tmp/t**
 | **# ls -l /tmp/t**
 |   -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
 
-|
-| **# bpftool prog dum jited pinned /sys/fs/bpf/prog**
+**# bpftool prog dum jited tag 005a3d2123620c8b**
 
 ::
 
@@ -83,6 +120,26 @@ EXAMPLES
     sub    $0x28,%rbp
     mov    %rbx,0x0(%rbp)
 
+|
+| **# mount -t bpf none /sys/fs/bpf/**
+| **# bpftool prog pin id 10 /sys/fs/bpf/prog**
+| **# ls -l /sys/fs/bpf/**
+|   -rw------- 1 root root 0 Jul 22 01:43 prog
+
+**# bpftool prog dum jited pinned /sys/fs/bpf/prog opcodes**
+
+::
+
+    push   %rbp
+    55
+    mov    %rsp,%rbp
+    48 89 e5
+    sub    $0x228,%rsp
+    48 81 ec 28 02 00 00
+    sub    $0x28,%rbp
+    48 83 ed 28
+    mov    %rbx,0x0(%rbp)
+    48 89 5d 00
 
 
 SEE ALSO
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 44e07799d54d..926c03d5a8da 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -10,7 +10,7 @@ tool for inspection and simple manipulation of eBPF programs and maps
 SYNOPSIS
 ========
 
-	**bpftool** *OBJECT* { *COMMAND* | **help** }
+	**bpftool** [*OPTIONS*] *OBJECT* { *COMMAND* | **help** }
 
 	**bpftool** **batch file** *FILE*
 
@@ -18,6 +18,9 @@ SYNOPSIS
 
 	*OBJECT* := { **map** | **program** }
 
+	*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
+	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
 	*MAP-COMMANDS* :=
 	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
 	| **pin** | **help** }
@@ -41,6 +44,13 @@ OPTIONS
 	-v, --version
 		  Print version number (similar to **bpftool version**).
 
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
 SEE ALSO
 ========
 	**bpftool-map**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 55ba0a04c102..78d9afb74ef4 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -70,11 +70,13 @@ static int do_help(int argc, char **argv)
 	}
 
 	fprintf(stderr,
-		"Usage: %s OBJECT { COMMAND | help }\n"
+		"Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n"
 		"       %s batch file FILE\n"
 		"       %s version\n"
 		"\n"
-		"       OBJECT := { prog | map }\n",
+		"       OBJECT := { prog | map }\n"
+		"       " HELP_SPEC_OPTIONS "\n"
+		"",
 		bin_name, bin_name, bin_name);
 
 	return 0;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 04c88b55d8c7..2f94bed03a8d 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -55,6 +55,8 @@
 
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
+#define HELP_SPEC_OPTIONS						\
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] }"
 
 enum bpf_obj_type {
 	BPF_OBJ_UNKNOWN,
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index a611f31f574f..e978ab23a77f 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -850,6 +850,7 @@ static int do_help(int argc, char **argv)
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       VALUE := { BYTES | MAP | PROG }\n"
 		"       UPDATE_FLAGS := { any | exist | noexist }\n"
+		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index e07f35ff80d1..250f80fd46aa 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -625,6 +625,7 @@ static int do_help(int argc, char **argv)
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_PROGRAM "\n"
+		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2]);
-- 
cgit v1.2.3


From 3fc27b71b894f5e2ad611297d5817b6092c96626 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 24 Oct 2017 20:11:28 -0700
Subject: tools: bpftool: try to mount bpffs if required for pinning objects

One possible cause of failure for `bpftool {prog|map} pin * file FILE`
is the FILE not being in an eBPF virtual file system (bpffs). In this
case, make bpftool attempt to mount bpffs on the parent directory of the
FILE. Then, if this operation is successful, try again to pin the
object.

The code for mnt_bpffs() is a copy of function bpf_mnt_fs() from
iproute2 package (under lib/bpf.c, taken at commit 4b73d52f8a81), with
modifications regarding handling of error messages.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/common.c | 71 ++++++++++++++++++++++++++++++++++++++++------
 tools/bpf/bpftool/main.h   |  2 ++
 2 files changed, 65 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index b2533f1cae3e..f0288269dae8 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -42,6 +42,7 @@
 #include <unistd.h>
 #include <linux/limits.h>
 #include <linux/magic.h>
+#include <sys/mount.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
 
@@ -59,6 +60,37 @@ static bool is_bpffs(char *path)
 	return (unsigned long)st_fs.f_type == BPF_FS_MAGIC;
 }
 
+static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
+{
+	bool bind_done = false;
+
+	while (mount("", target, "none", MS_PRIVATE | MS_REC, NULL)) {
+		if (errno != EINVAL || bind_done) {
+			snprintf(buff, bufflen,
+				 "mount --make-private %s failed: %s",
+				 target, strerror(errno));
+			return -1;
+		}
+
+		if (mount(target, target, "none", MS_BIND, NULL)) {
+			snprintf(buff, bufflen,
+				 "mount --bind %s %s failed: %s",
+				 target, target, strerror(errno));
+			return -1;
+		}
+
+		bind_done = true;
+	}
+
+	if (mount("bpf", target, "bpf", 0, "mode=0700")) {
+		snprintf(buff, bufflen, "mount -t bpf bpf %s failed: %s",
+			 target, strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 {
 	enum bpf_obj_type type;
@@ -89,8 +121,11 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 {
+	char err_str[ERR_MAX_LEN];
 	unsigned int id;
 	char *endptr;
+	char *file;
+	char *dir;
 	int err;
 	int fd;
 
@@ -117,16 +152,36 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	}
 
 	err = bpf_obj_pin(fd, *argv);
-	close(fd);
-	if (err) {
-		p_err("can't pin the object (%s): %s", *argv,
-		      errno == EACCES && !is_bpffs(dirname(*argv)) ?
-		    "directory not in bpf file system (bpffs)" :
-		    strerror(errno));
-		return -1;
+	if (!err)
+		goto out_close;
+
+	file = malloc(strlen(*argv) + 1);
+	strcpy(file, *argv);
+	dir = dirname(file);
+
+	if (errno != EPERM || is_bpffs(dir)) {
+		p_err("can't pin the object (%s): %s", *argv, strerror(errno));
+		goto out_free;
 	}
 
-	return 0;
+	/* Attempt to mount bpffs, then retry pinning. */
+	err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
+	if (!err) {
+		err = bpf_obj_pin(fd, *argv);
+		if (err)
+			p_err("can't pin the object (%s): %s", *argv,
+			      strerror(errno));
+	} else {
+		err_str[ERR_MAX_LEN - 1] = '\0';
+		p_err("can't mount BPF file system to pin the object (%s): %s",
+		      *argv, err_str);
+	}
+
+out_free:
+	free(file);
+out_close:
+	close(fd);
+	return err;
 }
 
 const char *get_fd_type_name(enum bpf_obj_type type)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 2f94bed03a8d..d315d01be645 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -51,6 +51,8 @@
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
 #define BAD_ARG()	({ p_err("what is '%s'?\n", *argv); -1; })
 
+#define ERR_MAX_LEN	1024
+
 #define BPF_TAG_FMT	"%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
 
 #define HELP_SPEC_PROGRAM						\
-- 
cgit v1.2.3


From 995231c820e3bd3633cb38bf4ea6f2541e1da331 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 26 Oct 2017 14:16:05 -0700
Subject: tools: bpftool: add bash completion for bpftool

Add a completion file for bash. The completion function runs bpftool
when needed, making it smart enough to help users complete ids or tags
for eBPF programs and maps currently on the system.

Update Makefile to install completion file to
/usr/share/bash-completion/completions when running `make install`.

Emacs file mode and (at the end) Vim modeline have been added, to keep
the style in use for most existing bash completion files. In this, it
differs from tools/perf/perf-completion.sh, which seems to be the only
other completion file among the kernel sources repository. This is also
valid for indent style: 4-space indents, as in other completion files.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Makefile                |   3 +
 tools/bpf/bpftool/bash-completion/bpftool | 354 ++++++++++++++++++++++++++++++
 2 files changed, 357 insertions(+)
 create mode 100644 tools/bpf/bpftool/bash-completion/bpftool

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 4f339824ca57..813826c50936 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -46,6 +46,7 @@ $(LIBBPF)-clean:
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null
 
 prefix = /usr
+bash_compdir ?= $(prefix)/share/bash-completion/completions
 
 CC = gcc
 
@@ -76,6 +77,8 @@ clean: $(LIBBPF)-clean
 
 install:
 	install $(OUTPUT)bpftool $(prefix)/sbin/bpftool
+	install -m 0755 -d $(bash_compdir)
+	install -m 0644 bash-completion/bpftool $(bash_compdir)
 
 doc:
 	$(Q)$(MAKE) -C Documentation/
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
new file mode 100644
index 000000000000..7febee05c8e7
--- /dev/null
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -0,0 +1,354 @@
+# bpftool(8) bash completion                               -*- shell-script -*-
+#
+# Copyright (C) 2017 Netronome Systems, Inc.
+#
+# This software is dual licensed under the GNU General License
+# Version 2, June 1991 as shown in the file COPYING in the top-level
+# directory of this source tree or the BSD 2-Clause License provided
+# below.  You have the option to license this software under the
+# complete terms of either license.
+#
+# The BSD 2-Clause License:
+#
+#     Redistribution and use in source and binary forms, with or
+#     without modification, are permitted provided that the following
+#     conditions are met:
+#
+#      1. Redistributions of source code must retain the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer.
+#
+#      2. Redistributions in binary form must reproduce the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer in the documentation and/or other materials
+#         provided with the distribution.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+#
+# Author: Quentin Monnet <quentin.monnet@netronome.com>
+
+# Takes a list of words in argument; each one of them is added to COMPREPLY if
+# it is not already present on the command line. Returns no value.
+_bpftool_once_attr()
+{
+    local w idx found
+    for w in $*; do
+        found=0
+        for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+            if [[ $w == ${words[idx]} ]]; then
+                found=1
+                break
+            fi
+        done
+        [[ $found -eq 0 ]] && \
+            COMPREPLY+=( $( compgen -W "$w" -- "$cur" ) )
+    done
+}
+
+# Takes a list of words in argument; adds them all to COMPREPLY if none of them
+# is already present on the command line. Returns no value.
+_bpftool_one_of_list()
+{
+    local w idx
+    for w in $*; do
+        for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+            [[ $w == ${words[idx]} ]] && return 1
+        done
+    done
+    COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) )
+}
+
+_bpftool_get_map_ids()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp map  2>&1 | \
+        command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+_bpftool_get_prog_ids()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
+        command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+_bpftool_get_prog_tags()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
+        command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
+}
+
+# For bpftool map update: retrieve type of the map to update.
+_bpftool_map_update_map_type()
+{
+    local keyword ref
+    for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+        if [[ ${words[$((idx-2))]} == "update" ]]; then
+            keyword=${words[$((idx-1))]}
+            ref=${words[$((idx))]}
+        fi
+    done
+    [[ -z $ref ]] && return 0
+
+    local type
+    type=$(bpftool -jp map show $keyword $ref | \
+        command sed -n 's/.*"type": "\(.*\)",$/\1/p')
+    printf $type
+}
+
+_bpftool_map_update_get_id()
+{
+    # Is it the map to update, or a map to insert into the map to update?
+    # Search for "value" keyword.
+    local idx value
+    for (( idx=7; idx < ${#words[@]}-1; idx++ )); do
+        if [[ ${words[idx]} == "value" ]]; then
+            value=1
+            break
+        fi
+    done
+    [[ $value -eq 0 ]] && _bpftool_get_map_ids && return 0
+
+    # Id to complete is for a value. It can be either prog id or map id. This
+    # depends on the type of the map to update.
+    local type=$(_bpftool_map_update_map_type)
+    case $type in
+        array_of_maps|hash_of_maps)
+            _bpftool_get_map_ids
+            return 0
+            ;;
+        prog_array)
+            _bpftool_get_prog_ids
+            return 0
+            ;;
+        *)
+            return 0
+            ;;
+    esac
+}
+
+_bpftool()
+{
+    local cur prev words objword
+    _init_completion || return
+
+    # Deal with simplest keywords
+    case $prev in
+        help|key|opcodes)
+            return 0
+            ;;
+        tag)
+            _bpftool_get_prog_tags
+            return 0
+            ;;
+        file|pinned)
+            _filedir
+            return 0
+            ;;
+        batch)
+            COMPREPLY=( $( compgen -W 'file' -- "$cur" ) )
+            return 0
+            ;;
+    esac
+
+    # Search for object and command
+    local object command cmdword
+    for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do
+        [[ -n $object ]] && command=${words[cmdword]} && break
+        [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]}
+    done
+
+    if [[ -z $object ]]; then
+        case $cur in
+            -*)
+                local c='--version --json --pretty'
+                COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
+                return 0
+                ;;
+            *)
+                COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \
+                    command sed \
+                    -e '/OBJECT := /!d' \
+                    -e 's/.*{//' \
+                    -e 's/}.*//' \
+                    -e 's/|//g' )" -- "$cur" ) )
+                COMPREPLY+=( $( compgen -W 'batch help' -- "$cur" ) )
+                return 0
+                ;;
+        esac
+    fi
+
+    [[ $command == help ]] && return 0
+
+    # Completion depends on object and command in use
+    case $object in
+        prog)
+            case $prev in
+                id)
+                    _bpftool_get_prog_ids
+                    return 0
+                    ;;
+            esac
+
+            local PROG_TYPE='id pinned tag'
+            case $command in
+                show)
+                    [[ $prev != "$command" ]] && return 0
+                    COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    return 0
+                    ;;
+                dump)
+                    case $prev in
+                        $command)
+                            COMPREPLY+=( $( compgen -W "xlated jited" -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                        xlated|jited)
+                            COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                    *)
+                            _bpftool_once_attr 'file'
+                            COMPREPLY+=( $( compgen -W 'opcodes' -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                pin)
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    else
+                        _filedir
+                    fi
+                    return 0
+                    ;;
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'dump help pin show' -- \
+                            "$cur" ) )
+                    ;;
+            esac
+            ;;
+        map)
+            local MAP_TYPE='id pinned'
+            case $command in
+                show|dump)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        *)
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                lookup|getnext|delete)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        key)
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'key'
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                update)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_map_update_get_id
+                            return 0
+                            ;;
+                        key)
+                            return 0
+                            ;;
+                        value)
+                            # We can have bytes, or references to a prog or a
+                            # map, depending on the type of the map to update.
+                            case $(_bpftool_map_update_map_type) in
+                                array_of_maps|hash_of_maps)
+                                    local MAP_TYPE='id pinned'
+                                    COMPREPLY+=( $( compgen -W "$MAP_TYPE" \
+                                        -- "$cur" ) )
+                                    return 0
+                                    ;;
+                                prog_array)
+                                    local PROG_TYPE='id pinned tag'
+                                    COMPREPLY+=( $( compgen -W "$PROG_TYPE" \
+                                        -- "$cur" ) )
+                                    return 0
+                                    ;;
+                                *)
+                                    return 0
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'key'
+                            local UPDATE_FLAGS='any exist noexist'
+                            for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+                                if [[ ${words[idx]} == 'value' ]]; then
+                                    # 'value' is present, but is not the last
+                                    # word i.e. we can now have UPDATE_FLAGS.
+                                    _bpftool_one_of_list "$UPDATE_FLAGS"
+                                    return 0
+                                fi
+                            done
+                            for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+                                if [[ ${words[idx]} == 'key' ]]; then
+                                    # 'key' is present, but is not the last
+                                    # word i.e. we can now have 'value'.
+                                    _bpftool_once_attr 'value'
+                                    return 0
+                                fi
+                            done
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                pin)
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    else
+                        _filedir
+                    fi
+                    return 0
+                    ;;
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'delete dump getnext help \
+                            lookup pin show update' -- "$cur" ) )
+                    ;;
+            esac
+            ;;
+    esac
+} &&
+complete -F _bpftool bpftool
+
+# ex: ts=4 sw=4 et filetype=sh
-- 
cgit v1.2.3


From 7dfbe5b64fe8f619bc056a7f81421e8beab373f1 Mon Sep 17 00:00:00 2001
From: "Brenda J. Butler" <bjb@mojatatu.com>
Date: Tue, 31 Oct 2017 14:25:46 -0400
Subject: tc-testing: very simple example test cases

As part of documentation, supply some very simple test cases
to illustrate how test cases work.  One test case shows
commands in the setup, command, verify and teardown stages.
Other test cases show how to have a working test case that
does not have commands in the setup, verify and/or teardown
stages.

Specifically, the command lists for setup and teardown can
be empty.  And the verify command must have a command, but
it can be /bin/true.  The regex must have a string, we
recommend a single space, and the count of matches must be
zero if you do not want to use the match feature of verify.
Verify will always look for a return code of success (0)
so we give /bin/true when we do not want to make a check
there.

Also, update the documentation for testcases to be more
specific in the cases of:

    - accepting non-success return codes in setup and
      teardown stages
    - how to write the test when no setup, teardown
      and/or verify are desired.

To run the example test cases:

    $ sudo -E ./tdc.py -f creating-testcases/example.json -l
    1f: (example) simple test to test framework
    2f: (example) simple test, no need for verify
    3f: (example) simple test, no need for setup or teardown (or verify)
    $ sudo -E ./tdc.py -f creating-testcases/example.json
    Test 1f: simple test to test framework
    Test 2f: simple test, no need for verify
    Test 3f: simple test, no need for setup or teardown (or verify)
    All test results:

    1..3
    ok 1 1f simple test to test framework
    ok 2 2f simple test, no need for verify
    ok 3 3f simple test, no need for setup or teardown (or verify)

    $

Signed-off-by: Brenda J. Butler <bjb@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../creating-testcases/AddingTestCases.txt         | 12 +++++
 .../tc-testing/creating-testcases/example.json     | 55 ++++++++++++++++++++++
 .../tc-testing/creating-testcases/template.json    | 15 +++++-
 3 files changed, 80 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/creating-testcases/example.json

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
index 4e09257bc443..00438331ba47 100644
--- a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
+++ b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
@@ -34,6 +34,12 @@ category:     A list of single-word descriptions covering what the command
 setup:        The list of commands required to ensure the command under test
               succeeds. For example: if testing a filter, the command to create
               the qdisc would appear here.
+	      This list can be empty.
+	      Each command can be a string to be executed, or a list consisting
+	      of a string which is a command to be executed, followed by 1 or
+	      more acceptable exit codes for this command.
+	      If only a string is given for the command, then an exit code of 0
+	      will be expected.
 cmdUnderTest: The tc command being tested itself.
 expExitCode:  The code returned by the command under test upon its termination.
               tdc will compare this value against the actual returned value.
@@ -49,6 +55,12 @@ matchCount:   How many times the regex in matchPattern should match. A value
 teardown:     The list of commands to clean up after the test is completed.
               The environment should be returned to the same state as when
               this test was started: qdiscs deleted, actions flushed, etc.
+	      This list can be empty.
+	      Each command can be a string to be executed, or a list consisting
+	      of a string which is a command to be executed, followed by 1 or
+	      more acceptable exit codes for this command.
+	      If only a string is given for the command, then an exit code of 0
+	      will be expected.
 
 
 SETUP/TEARDOWN ERRORS
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/example.json b/tools/testing/selftests/tc-testing/creating-testcases/example.json
new file mode 100644
index 000000000000..5ec501200970
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/creating-testcases/example.json
@@ -0,0 +1,55 @@
+[
+    {
+        "id": "1f",
+        "name": "simple test to test framework",
+        "category": [
+            "example"
+        ],
+        "setup": [
+            "mkdir mytest"
+        ],
+        "cmdUnderTest": "touch mytest/blorfl",
+        "expExitCode": "0",
+        "verifyCmd": "ls mytest/* | grep '[b]lorfl'",
+        "matchPattern": "orfl",
+        "matchCount": "1",
+        "teardown": [
+            "rm -rf mytest"
+        ]
+    },
+    {
+        "id": "2f",
+        "name": "simple test, no need for verify",
+        "category": [
+            "example"
+        ],
+        "setup": [
+            "mkdir mytest",
+            "touch mytest/blorfl"
+        ],
+        "cmdUnderTest": "ls mytest/blorfl",
+        "expExitCode": "0",
+        "verifyCmd": "/bin/true",
+        "matchPattern": " ",
+        "matchCount": "0",
+        "teardown": [
+            "rm -rf mytest"
+        ]
+    },
+    {
+        "id": "3f",
+        "name": "simple test, no need for setup or teardown (or verify)",
+        "category": [
+            "example"
+        ],
+        "setup": [
+        ],
+        "cmdUnderTest": "ip l l lo",
+        "expExitCode": "0",
+        "verifyCmd": "/bin/true",
+        "matchPattern": " ",
+        "matchCount": "0",
+        "teardown": [
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/template.json b/tools/testing/selftests/tc-testing/creating-testcases/template.json
index 87971744bdd4..8b99b86d65bd 100644
--- a/tools/testing/selftests/tc-testing/creating-testcases/template.json
+++ b/tools/testing/selftests/tc-testing/creating-testcases/template.json
@@ -26,7 +26,13 @@
             ""
         ],
         "setup": [
-            ""
+            "",
+	    [
+		"",
+		0,
+		1,
+		255
+	    ]
         ],
         "cmdUnderTest": "",
         "expExitCode": "",
@@ -34,7 +40,12 @@
         "matchPattern": "",
         "matchCount": "",
         "teardown": [
-            ""
+            "",
+	    [
+		"",
+		0,
+		255
+            ]
         ]
     }
 ]
-- 
cgit v1.2.3


From a5a5efe9998d6f28263324b8aa3e77a1b6cc465e Mon Sep 17 00:00:00 2001
From: "Brenda J. Butler" <bjb@mojatatu.com>
Date: Tue, 31 Oct 2017 14:26:54 -0400
Subject: tc-testing: gitignore, ignore standard python artifacts

Ignore .pyc files, "python compiled" files, that get created
when a python script is run.  They should never be committed.

Signed-off-by: Brenda J. Butler <bjb@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index c18dd8d83cee..7a60b85e148f 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1 +1,2 @@
 __pycache__/
+*.pyc
-- 
cgit v1.2.3


From 181d6610f5311868f092d033f0273140dd44fb8a Mon Sep 17 00:00:00 2001
From: "Brenda J. Butler" <bjb@mojatatu.com>
Date: Tue, 31 Oct 2017 14:27:28 -0400
Subject: tc-testing: split config file

Move the config customization into a site-local file
tdc_config_local.py, so that updates of the tdc test
software does not require hand-editing of the config.
This patch includes a template for the site-local
customization file.

In addition, this makes it easy to revert to a stock
tdc environment for testing the test framework and/or
the core tests.

Also it makes it harder for any custom config to be
submitted back to the kernel tdc.

Signed-off-by: Brenda J. Butler <bjb@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc_config.py   | 14 +++++++++++++
 .../tc-testing/tdc_config_local_template.py        | 23 ++++++++++++++++++++++
 2 files changed, 37 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tdc_config_local_template.py

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index b6352515c1b5..596558445713 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -17,3 +17,17 @@ NAMES = {
           # Name of the namespace to use
           'NS': 'tcut'
         }
+
+
+ENVIR = { }
+
+# put customizations in tdc_config_local.py
+try:
+    from tdc_config_local import *
+except ImportError as ie:
+    pass
+
+try:
+    NAMES.update(EXTRA_NAMES)
+except NameError as ne:
+    pass
diff --git a/tools/testing/selftests/tc-testing/tdc_config_local_template.py b/tools/testing/selftests/tc-testing/tdc_config_local_template.py
new file mode 100644
index 000000000000..d48fc732a399
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_config_local_template.py
@@ -0,0 +1,23 @@
+"""
+tdc_config_local.py - tdc plugin-writer-specified values
+
+Copyright (C) 2017 bjb@mojatatu.com
+"""
+
+import os
+
+ENVIR = os.environ.copy()
+
+ENV_LD_LIBRARY_PATH = os.getenv('LD_LIBRARY_PATH', '')
+ENV_OTHER_LIB = os.getenv('OTHER_LIB', '')
+
+
+# example adding value to NAMES, without editing tdc_config.py
+EXTRA_NAMES = dict()
+EXTRA_NAMES['SOME_BIN'] = os.path.join(os.getenv('OTHER_BIN', ''), 'some_bin')
+
+
+# example adding values to ENVIR, without editing tdc_config.py
+ENVIR['VALGRIND_LIB'] = '/usr/lib/valgrind'
+ENVIR['VALGRIND_BIN'] = '/usr/bin/valgrind'
+ENVIR['VGDB_BIN'] = '/usr/bin/vgdb'
-- 
cgit v1.2.3


From 7ae677fb85f46c6b1c0545a0558c507ab940d7c4 Mon Sep 17 00:00:00 2001
From: "Brenda J. Butler" <bjb@mojatatu.com>
Date: Tue, 31 Oct 2017 14:28:02 -0400
Subject: tc-testing: correction to docstring in get_unique_item

Signed-off-by: Brenda J. Butler <bjb@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc_helper.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py
index c3254f861fb2..6f99a4efe761 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -15,7 +15,7 @@ def get_categorized_testlist(alltests, ucat):
 
 
 def get_unique_item(lst):
-    """ For a list, return a set of the unique items in the list. """
+    """ For a list, return a list of the unique items in the list. """
     return list(set(lst))
 
 
-- 
cgit v1.2.3


From 6c26c3fbc3295ce71f5e03caccc9eeb7369123ca Mon Sep 17 00:00:00 2001
From: "Brenda J. Butler" <bjb@mojatatu.com>
Date: Tue, 31 Oct 2017 14:28:35 -0400
Subject: tc-testing: better check if thing is list

Check if tcase[k] is an instance of a list (is or is derived from list)
instead of checking if it is a list.

This will be useful if the data structures change to be something
that implements list, instead of being an actual list.  In that
case, this code will not have to change.

Signed-off-by: Brenda J. Butler <bjb@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc_helper.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py
index 6f99a4efe761..d935cbc34cc3 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -57,7 +57,7 @@ def print_sll(items):
 def print_test_case(tcase):
     """ Pretty-printing of a given test case. """
     for k in tcase.keys():
-        if (type(tcase[k]) == list):
+        if (isinstance(tcase[k], list)):
             print(k + ":")
             print_list(tcase[k])
         else:
-- 
cgit v1.2.3


From 170b8ffa71412eeacb20589b807f4bc75a61e507 Mon Sep 17 00:00:00 2001
From: "Brenda J. Butler" <bjb@mojatatu.com>
Date: Tue, 31 Oct 2017 14:29:03 -0400
Subject: tc-testing: better test case file error reporting

tdc.py reads a bunch of test cases in json files.  When a json file
cannot be parsed, tdc just exits and does not run any tests.

This patch will cause tdc to print a message with the file name and
line number, then that file will be ignored and the rest of the tests
will be processed.

Signed-off-by: Brenda J. Butler <bjb@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc.py | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index 5508730ee1ea..a674fe9a7f1e 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -179,15 +179,20 @@ def has_blank_ids(idlist):
 
 def load_from_file(filename):
     """
-    Open the JSON file containing the test cases and return them as an
-    ordered dictionary object.
-    """
-    with open(filename) as test_data:
-        testlist = json.load(test_data, object_pairs_hook=OrderedDict)
-    idlist = get_id_list(testlist)
-    if (has_blank_ids(idlist)):
-        for k in testlist:
-            k['filename'] = filename
+    Open the JSON file containing the test cases and return them
+    as list of ordered dictionary objects.
+    """
+    try:
+        with open(filename) as test_data:
+            testlist = json.load(test_data, object_pairs_hook=OrderedDict)
+    except json.JSONDecodeError as jde:
+        print('IGNORING test case file {}\n\tBECAUSE:  {}'.format(filename, jde))
+        testlist = list()
+    else:
+        idlist = get_id_list(testlist)
+        if (has_blank_ids(idlist)):
+            for k in testlist:
+                k['filename'] = filename
     return testlist
 
 
-- 
cgit v1.2.3


From 81ba4e1ac4f1d3e9d980ca0f003dd3038559b3fa Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Sat, 28 Oct 2017 17:17:13 -0700
Subject: selftests/bpf: remove useless bpf_trace_printk

sockmap test is using two programs that use bpf_trace_printk()
which prints into trace_pipe, but nothing is reading it.
Remove it.

Fixes: 6f6d33f3b3d0 ("bpf: selftests add sockmap tests")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/sockmap_parse_prog.c   | 3 ---
 tools/testing/selftests/bpf/sockmap_verdict_prog.c | 2 --
 2 files changed, 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c
index fae3b96c3aa4..a1dec2b6d9c5 100644
--- a/tools/testing/selftests/bpf/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c
@@ -29,9 +29,6 @@ int bpf_prog1(struct __sk_buff *skb)
 	 * fields.
 	 */
 	d[7] = 1;
-
-	bpf_printk("parse: data[0] = (%u): local_port %i remote %i\n",
-		   d[0], lport, bpf_ntohl(rport));
 	return skb->len;
 }
 
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
index 2cd2d552938b..d7bea972cb21 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -58,8 +58,6 @@ int bpf_prog2(struct __sk_buff *skb)
 	d[6] = 0xe;
 	d[7] = 0xf;
 
-	bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
-
 	if (!map)
 		return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
 	return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
-- 
cgit v1.2.3


From b06723da824af1e979eb1699623881b5f45a783c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 1 Nov 2017 23:58:09 +0100
Subject: bpf: minor cleanups after merge

Two minor cleanups after Dave's recent merge in f8ddadc4db6c
("Merge git://git.kernel.org...") of net into net-next in
order to get the code in line with what was done originally
in the net tree: i) use max() instead of max_t() since both
ranges are u16, ii) don't split the direct access test cases
in the middle with bpf_exit test cases from 390ee7e29fc
("bpf: enforce return code for cgroup-bpf programs").

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       |   2 +-
 tools/testing/selftests/bpf/test_verifier.c | 144 ++++++++++++++--------------
 2 files changed, 73 insertions(+), 73 deletions(-)

(limited to 'tools')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2bb6d6aa7085..2cc3e9486a1f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2532,7 +2532,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 			continue;
 		reg = &state->stack[i].spilled_ptr;
 		if (reg->type == type && reg->id == dst_reg->id)
-			reg->range = max_t(u16, reg->range, new_range);
+			reg->range = max(reg->range, new_range);
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1b93941bdfea..3b38a3d2eebd 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -7249,78 +7249,6 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
-	{
-		"bpf_exit with invalid return code. test1",
-		.insns = {
-			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-			BPF_EXIT_INSN(),
-		},
-		.errstr = "R0 has value (0x0; 0xffffffff)",
-		.result = REJECT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
-	{
-		"bpf_exit with invalid return code. test2",
-		.insns = {
-			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.result = ACCEPT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
-	{
-		"bpf_exit with invalid return code. test3",
-		.insns = {
-			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3),
-			BPF_EXIT_INSN(),
-		},
-		.errstr = "R0 has value (0x0; 0x3)",
-		.result = REJECT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
-	{
-		"bpf_exit with invalid return code. test4",
-		.insns = {
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.result = ACCEPT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
-	{
-		"bpf_exit with invalid return code. test5",
-		.insns = {
-			BPF_MOV64_IMM(BPF_REG_0, 2),
-			BPF_EXIT_INSN(),
-		},
-		.errstr = "R0 has value (0x2; 0x0)",
-		.result = REJECT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
-	{
-		"bpf_exit with invalid return code. test6",
-		.insns = {
-			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-			BPF_EXIT_INSN(),
-		},
-		.errstr = "R0 is not a known value (ctx)",
-		.result = REJECT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
-	{
-		"bpf_exit with invalid return code. test7",
-		.insns = {
-			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4),
-			BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2),
-			BPF_EXIT_INSN(),
-		},
-		.errstr = "R0 has unknown scalar value",
-		.result = REJECT,
-		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	},
 	{
 		"XDP pkt read, pkt_end >= pkt_data', bad access 1",
 		.insns = {
@@ -7470,6 +7398,78 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_XDP,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"bpf_exit with invalid return code. test1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x0; 0xffffffff)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test3",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x0; 0x3)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x2; 0x0)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 is not a known value (ctx)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test7",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has unknown scalar value",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit v1.2.3


From 634eab11bd96d60d3a877182baa5b4b8bbed8685 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 1 Nov 2017 23:58:11 +0100
Subject: bpf: add test cases to bpf selftests to cover all meta tests

Lets also add test cases to cover all possible data_meta access tests
for good/bad access cases so we keep tracking them.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 442 ++++++++++++++++++++++++++++
 1 file changed, 442 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3b38a3d2eebd..bb3c4ad8c59f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -7398,6 +7398,448 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_XDP,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"XDP pkt read, pkt_meta' > pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' > pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' > pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data > pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data > pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data > pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' < pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' < pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' < pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data < pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data < pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data < pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' >= pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' >= pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' >= pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data >= pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data >= pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data >= pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' <= pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' <= pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_meta' <= pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data <= pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data <= pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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_data <= pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			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,
+	},
 	{
 		"bpf_exit with invalid return code. test1",
 		.insns = {
-- 
cgit v1.2.3


From cdc89c91987bd6efa962b36d4ea86d0c9152eb11 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Thu, 2 Nov 2017 17:09:45 +0900
Subject: tools: bpf: handle long path in jit disasm

Use PATH_MAX instead of hardcoded array size 256

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpf_jit_disasm.c     | 3 ++-
 tools/bpf/bpftool/jit_disasm.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c
index 422d9abd666a..75bf526a0168 100644
--- a/tools/bpf/bpf_jit_disasm.c
+++ b/tools/bpf/bpf_jit_disasm.c
@@ -27,6 +27,7 @@
 #include <sys/klog.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <limits.h>
 
 #define CMD_ACTION_SIZE_BUFFER		10
 #define CMD_ACTION_READ_ALL		3
@@ -51,7 +52,7 @@ static void get_exec_path(char *tpath, size_t size)
 static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
 {
 	int count, i, pc = 0;
-	char tpath[256];
+	char tpath[PATH_MAX];
 	struct disassemble_info info;
 	disassembler_ftype disassemble;
 	bfd *bfdf;
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 5937e134e408..1551d3918d4c 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -21,6 +21,7 @@
 #include <dis-asm.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <limits.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -80,7 +81,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
 	disassembler_ftype disassemble;
 	struct disassemble_info info;
 	int count, i, pc = 0;
-	char tpath[256];
+	char tpath[PATH_MAX];
 	bfd *bfdf;
 
 	if (!len)
-- 
cgit v1.2.3


From aa9ad44a42b4cf4387f8ecddaf8e51707fdcda5a Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Wed, 23 Aug 2017 12:48:26 -0700
Subject: libnvdimm: move poison list functions to a new 'badrange' file

nfit_test needs to use the poison list manipulation code as well. Make
it more generic and in the process rename poison to badrange, and move
all the related helpers to a new file.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
[vishal: Add badrange.o to nfit_test's Kbuild]
[vishal: add a missed include in bus.c for the new badrange functions]
[vishal: rename all instances of 'be' to 'bre']
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit/core.c    |   2 +-
 drivers/acpi/nfit/mce.c     |   2 +-
 drivers/nvdimm/Makefile     |   1 +
 drivers/nvdimm/badrange.c   | 294 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/nvdimm/bus.c        |  24 ++--
 drivers/nvdimm/core.c       | 260 +--------------------------------------
 drivers/nvdimm/nd-core.h    |   3 +-
 drivers/nvdimm/nd.h         |   6 -
 include/linux/libnvdimm.h   |  21 +++-
 tools/testing/nvdimm/Kbuild |   1 +
 10 files changed, 332 insertions(+), 282 deletions(-)
 create mode 100644 drivers/nvdimm/badrange.c

(limited to 'tools')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index aa75d67ceee9..8043bfde7c63 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2486,7 +2486,7 @@ static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc,
 		if (ars_status->out_length
 				< 44 + sizeof(struct nd_ars_record) * (i + 1))
 			break;
-		rc = nvdimm_bus_add_poison(nvdimm_bus,
+		rc = nvdimm_bus_add_badrange(nvdimm_bus,
 				ars_status->records[i].err_address,
 				ars_status->records[i].length);
 		if (rc)
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index feeb95d574fa..b92921439657 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -67,7 +67,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 			continue;
 
 		/* If this fails due to an -ENOMEM, there is little we can do */
-		nvdimm_bus_add_poison(acpi_desc->nvdimm_bus,
+		nvdimm_bus_add_badrange(acpi_desc->nvdimm_bus,
 				ALIGN(mce->addr, L1_CACHE_BYTES),
 				L1_CACHE_BYTES);
 		nvdimm_region_notify(nfit_spa->nd_region,
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 909554c3f955..ca6d325438a3 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -20,6 +20,7 @@ libnvdimm-y += region_devs.o
 libnvdimm-y += region.o
 libnvdimm-y += namespace_devs.o
 libnvdimm-y += label.o
+libnvdimm-y += badrange.o
 libnvdimm-$(CONFIG_ND_CLAIM) += claim.o
 libnvdimm-$(CONFIG_BTT) += btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o
diff --git a/drivers/nvdimm/badrange.c b/drivers/nvdimm/badrange.c
new file mode 100644
index 000000000000..0b67dcf43234
--- /dev/null
+++ b/drivers/nvdimm/badrange.c
@@ -0,0 +1,294 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ */
+#include <linux/libnvdimm.h>
+#include <linux/badblocks.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/device.h>
+#include <linux/ctype.h>
+#include <linux/ndctl.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include "nd-core.h"
+#include "nd.h"
+
+void badrange_init(struct badrange *badrange)
+{
+	INIT_LIST_HEAD(&badrange->list);
+	spin_lock_init(&badrange->lock);
+}
+EXPORT_SYMBOL_GPL(badrange_init);
+
+static void append_badrange_entry(struct badrange *badrange,
+		struct badrange_entry *bre, u64 addr, u64 length)
+{
+	lockdep_assert_held(&badrange->lock);
+	bre->start = addr;
+	bre->length = length;
+	list_add_tail(&bre->list, &badrange->list);
+}
+
+static int alloc_and_append_badrange_entry(struct badrange *badrange,
+		u64 addr, u64 length, gfp_t flags)
+{
+	struct badrange_entry *bre;
+
+	bre = kzalloc(sizeof(*bre), flags);
+	if (!bre)
+		return -ENOMEM;
+
+	append_badrange_entry(badrange, bre, addr, length);
+	return 0;
+}
+
+static int add_badrange(struct badrange *badrange, u64 addr, u64 length)
+{
+	struct badrange_entry *bre, *bre_new;
+
+	spin_unlock(&badrange->lock);
+	bre_new = kzalloc(sizeof(*bre_new), GFP_KERNEL);
+	spin_lock(&badrange->lock);
+
+	if (list_empty(&badrange->list)) {
+		if (!bre_new)
+			return -ENOMEM;
+		append_badrange_entry(badrange, bre_new, addr, length);
+		return 0;
+	}
+
+	/*
+	 * There is a chance this is a duplicate, check for those first.
+	 * This will be the common case as ARS_STATUS returns all known
+	 * errors in the SPA space, and we can't query it per region
+	 */
+	list_for_each_entry(bre, &badrange->list, list)
+		if (bre->start == addr) {
+			/* If length has changed, update this list entry */
+			if (bre->length != length)
+				bre->length = length;
+			kfree(bre_new);
+			return 0;
+		}
+
+	/*
+	 * If not a duplicate or a simple length update, add the entry as is,
+	 * as any overlapping ranges will get resolved when the list is consumed
+	 * and converted to badblocks
+	 */
+	if (!bre_new)
+		return -ENOMEM;
+	append_badrange_entry(badrange, bre_new, addr, length);
+
+	return 0;
+}
+
+int badrange_add(struct badrange *badrange, u64 addr, u64 length)
+{
+	int rc;
+
+	spin_lock(&badrange->lock);
+	rc = add_badrange(badrange, addr, length);
+	spin_unlock(&badrange->lock);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(badrange_add);
+
+void badrange_forget(struct badrange *badrange, phys_addr_t start,
+		unsigned int len)
+{
+	struct list_head *badrange_list = &badrange->list;
+	u64 clr_end = start + len - 1;
+	struct badrange_entry *bre, *next;
+
+	spin_lock(&badrange->lock);
+	WARN_ON_ONCE(list_empty(badrange_list));
+
+	/*
+	 * [start, clr_end] is the badrange interval being cleared.
+	 * [bre->start, bre_end] is the badrange_list entry we're comparing
+	 * the above interval against. The badrange list entry may need
+	 * to be modified (update either start or length), deleted, or
+	 * split into two based on the overlap characteristics
+	 */
+
+	list_for_each_entry_safe(bre, next, badrange_list, list) {
+		u64 bre_end = bre->start + bre->length - 1;
+
+		/* Skip intervals with no intersection */
+		if (bre_end < start)
+			continue;
+		if (bre->start >  clr_end)
+			continue;
+		/* Delete completely overlapped badrange entries */
+		if ((bre->start >= start) && (bre_end <= clr_end)) {
+			list_del(&bre->list);
+			kfree(bre);
+			continue;
+		}
+		/* Adjust start point of partially cleared entries */
+		if ((start <= bre->start) && (clr_end > bre->start)) {
+			bre->length -= clr_end - bre->start + 1;
+			bre->start = clr_end + 1;
+			continue;
+		}
+		/* Adjust bre->length for partial clearing at the tail end */
+		if ((bre->start < start) && (bre_end <= clr_end)) {
+			/* bre->start remains the same */
+			bre->length = start - bre->start;
+			continue;
+		}
+		/*
+		 * If clearing in the middle of an entry, we split it into
+		 * two by modifying the current entry to represent one half of
+		 * the split, and adding a new entry for the second half.
+		 */
+		if ((bre->start < start) && (bre_end > clr_end)) {
+			u64 new_start = clr_end + 1;
+			u64 new_len = bre_end - new_start + 1;
+
+			/* Add new entry covering the right half */
+			alloc_and_append_badrange_entry(badrange, new_start,
+					new_len, GFP_NOWAIT);
+			/* Adjust this entry to cover the left half */
+			bre->length = start - bre->start;
+			continue;
+		}
+	}
+	spin_unlock(&badrange->lock);
+}
+EXPORT_SYMBOL_GPL(badrange_forget);
+
+static void set_badblock(struct badblocks *bb, sector_t s, int num)
+{
+	dev_dbg(bb->dev, "Found a bad range (0x%llx, 0x%llx)\n",
+			(u64) s * 512, (u64) num * 512);
+	/* this isn't an error as the hardware will still throw an exception */
+	if (badblocks_set(bb, s, num, 1))
+		dev_info_once(bb->dev, "%s: failed for sector %llx\n",
+				__func__, (u64) s);
+}
+
+/**
+ * __add_badblock_range() - Convert a physical address range to bad sectors
+ * @bb:		badblocks instance to populate
+ * @ns_offset:	namespace offset where the error range begins (in bytes)
+ * @len:	number of bytes of badrange to be added
+ *
+ * This assumes that the range provided with (ns_offset, len) is within
+ * the bounds of physical addresses for this namespace, i.e. lies in the
+ * interval [ns_start, ns_start + ns_size)
+ */
+static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
+{
+	const unsigned int sector_size = 512;
+	sector_t start_sector, end_sector;
+	u64 num_sectors;
+	u32 rem;
+
+	start_sector = div_u64(ns_offset, sector_size);
+	end_sector = div_u64_rem(ns_offset + len, sector_size, &rem);
+	if (rem)
+		end_sector++;
+	num_sectors = end_sector - start_sector;
+
+	if (unlikely(num_sectors > (u64)INT_MAX)) {
+		u64 remaining = num_sectors;
+		sector_t s = start_sector;
+
+		while (remaining) {
+			int done = min_t(u64, remaining, INT_MAX);
+
+			set_badblock(bb, s, done);
+			remaining -= done;
+			s += done;
+		}
+	} else
+		set_badblock(bb, start_sector, num_sectors);
+}
+
+static void badblocks_populate(struct badrange *badrange,
+		struct badblocks *bb, const struct resource *res)
+{
+	struct badrange_entry *bre;
+
+	if (list_empty(&badrange->list))
+		return;
+
+	list_for_each_entry(bre, &badrange->list, list) {
+		u64 bre_end = bre->start + bre->length - 1;
+
+		/* Discard intervals with no intersection */
+		if (bre_end < res->start)
+			continue;
+		if (bre->start >  res->end)
+			continue;
+		/* Deal with any overlap after start of the namespace */
+		if (bre->start >= res->start) {
+			u64 start = bre->start;
+			u64 len;
+
+			if (bre_end <= res->end)
+				len = bre->length;
+			else
+				len = res->start + resource_size(res)
+					- bre->start;
+			__add_badblock_range(bb, start - res->start, len);
+			continue;
+		}
+		/*
+		 * Deal with overlap for badrange starting before
+		 * the namespace.
+		 */
+		if (bre->start < res->start) {
+			u64 len;
+
+			if (bre_end < res->end)
+				len = bre->start + bre->length - res->start;
+			else
+				len = resource_size(res);
+			__add_badblock_range(bb, 0, len);
+		}
+	}
+}
+
+/**
+ * nvdimm_badblocks_populate() - Convert a list of badranges to badblocks
+ * @region: parent region of the range to interrogate
+ * @bb: badblocks instance to populate
+ * @res: resource range to consider
+ *
+ * The badrange list generated during bus initialization may contain
+ * multiple, possibly overlapping physical address ranges.  Compare each
+ * of these ranges to the resource range currently being initialized,
+ * and add badblocks entries for all matching sub-ranges
+ */
+void nvdimm_badblocks_populate(struct nd_region *nd_region,
+		struct badblocks *bb, const struct resource *res)
+{
+	struct nvdimm_bus *nvdimm_bus;
+
+	if (!is_memory(&nd_region->dev)) {
+		dev_WARN_ONCE(&nd_region->dev, 1,
+				"%s only valid for pmem regions\n", __func__);
+		return;
+	}
+	nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+
+	nvdimm_bus_lock(&nvdimm_bus->dev);
+	badblocks_populate(&nvdimm_bus->badrange, bb, res);
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+}
+EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index baf283986a7e..0a5e6cd758fe 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -11,6 +11,7 @@
  * General Public License for more details.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/libnvdimm.h>
 #include <linux/sched/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
@@ -221,7 +222,7 @@ static void nvdimm_account_cleared_poison(struct nvdimm_bus *nvdimm_bus,
 		phys_addr_t phys, u64 cleared)
 {
 	if (cleared > 0)
-		nvdimm_forget_poison(nvdimm_bus, phys, cleared);
+		badrange_forget(&nvdimm_bus->badrange, phys, cleared);
 
 	if (cleared > 0 && cleared / 512)
 		nvdimm_clear_badblocks_regions(nvdimm_bus, phys, cleared);
@@ -344,11 +345,10 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 		return NULL;
 	INIT_LIST_HEAD(&nvdimm_bus->list);
 	INIT_LIST_HEAD(&nvdimm_bus->mapping_list);
-	INIT_LIST_HEAD(&nvdimm_bus->poison_list);
 	init_waitqueue_head(&nvdimm_bus->probe_wait);
 	nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
 	mutex_init(&nvdimm_bus->reconfig_mutex);
-	spin_lock_init(&nvdimm_bus->poison_lock);
+	badrange_init(&nvdimm_bus->badrange);
 	if (nvdimm_bus->id < 0) {
 		kfree(nvdimm_bus);
 		return NULL;
@@ -395,15 +395,15 @@ static int child_unregister(struct device *dev, void *data)
 	return 0;
 }
 
-static void free_poison_list(struct list_head *poison_list)
+static void free_badrange_list(struct list_head *badrange_list)
 {
-	struct nd_poison *pl, *next;
+	struct badrange_entry *bre, *next;
 
-	list_for_each_entry_safe(pl, next, poison_list, list) {
-		list_del(&pl->list);
-		kfree(pl);
+	list_for_each_entry_safe(bre, next, badrange_list, list) {
+		list_del(&bre->list);
+		kfree(bre);
 	}
-	list_del_init(poison_list);
+	list_del_init(badrange_list);
 }
 
 static int nd_bus_remove(struct device *dev)
@@ -417,9 +417,9 @@ static int nd_bus_remove(struct device *dev)
 	nd_synchronize();
 	device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
 
-	spin_lock(&nvdimm_bus->poison_lock);
-	free_poison_list(&nvdimm_bus->poison_list);
-	spin_unlock(&nvdimm_bus->poison_lock);
+	spin_lock(&nvdimm_bus->badrange.lock);
+	free_badrange_list(&nvdimm_bus->badrange.list);
+	spin_unlock(&nvdimm_bus->badrange.lock);
 
 	nvdimm_bus_destroy_ndctl(nvdimm_bus);
 
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index bb71f0cf8f5d..1dc527660637 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -398,265 +398,11 @@ struct attribute_group nvdimm_bus_attribute_group = {
 };
 EXPORT_SYMBOL_GPL(nvdimm_bus_attribute_group);
 
-static void set_badblock(struct badblocks *bb, sector_t s, int num)
+int nvdimm_bus_add_badrange(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 {
-	dev_dbg(bb->dev, "Found a poison range (0x%llx, 0x%llx)\n",
-			(u64) s * 512, (u64) num * 512);
-	/* this isn't an error as the hardware will still throw an exception */
-	if (badblocks_set(bb, s, num, 1))
-		dev_info_once(bb->dev, "%s: failed for sector %llx\n",
-				__func__, (u64) s);
+	return badrange_add(&nvdimm_bus->badrange, addr, length);
 }
-
-/**
- * __add_badblock_range() - Convert a physical address range to bad sectors
- * @bb:		badblocks instance to populate
- * @ns_offset:	namespace offset where the error range begins (in bytes)
- * @len:	number of bytes of poison to be added
- *
- * This assumes that the range provided with (ns_offset, len) is within
- * the bounds of physical addresses for this namespace, i.e. lies in the
- * interval [ns_start, ns_start + ns_size)
- */
-static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
-{
-	const unsigned int sector_size = 512;
-	sector_t start_sector, end_sector;
-	u64 num_sectors;
-	u32 rem;
-
-	start_sector = div_u64(ns_offset, sector_size);
-	end_sector = div_u64_rem(ns_offset + len, sector_size, &rem);
-	if (rem)
-		end_sector++;
-	num_sectors = end_sector - start_sector;
-
-	if (unlikely(num_sectors > (u64)INT_MAX)) {
-		u64 remaining = num_sectors;
-		sector_t s = start_sector;
-
-		while (remaining) {
-			int done = min_t(u64, remaining, INT_MAX);
-
-			set_badblock(bb, s, done);
-			remaining -= done;
-			s += done;
-		}
-	} else
-		set_badblock(bb, start_sector, num_sectors);
-}
-
-static void badblocks_populate(struct list_head *poison_list,
-		struct badblocks *bb, const struct resource *res)
-{
-	struct nd_poison *pl;
-
-	if (list_empty(poison_list))
-		return;
-
-	list_for_each_entry(pl, poison_list, list) {
-		u64 pl_end = pl->start + pl->length - 1;
-
-		/* Discard intervals with no intersection */
-		if (pl_end < res->start)
-			continue;
-		if (pl->start >  res->end)
-			continue;
-		/* Deal with any overlap after start of the namespace */
-		if (pl->start >= res->start) {
-			u64 start = pl->start;
-			u64 len;
-
-			if (pl_end <= res->end)
-				len = pl->length;
-			else
-				len = res->start + resource_size(res)
-					- pl->start;
-			__add_badblock_range(bb, start - res->start, len);
-			continue;
-		}
-		/* Deal with overlap for poison starting before the namespace */
-		if (pl->start < res->start) {
-			u64 len;
-
-			if (pl_end < res->end)
-				len = pl->start + pl->length - res->start;
-			else
-				len = resource_size(res);
-			__add_badblock_range(bb, 0, len);
-		}
-	}
-}
-
-/**
- * nvdimm_badblocks_populate() - Convert a list of poison ranges to badblocks
- * @region: parent region of the range to interrogate
- * @bb: badblocks instance to populate
- * @res: resource range to consider
- *
- * The poison list generated during bus initialization may contain
- * multiple, possibly overlapping physical address ranges.  Compare each
- * of these ranges to the resource range currently being initialized,
- * and add badblocks entries for all matching sub-ranges
- */
-void nvdimm_badblocks_populate(struct nd_region *nd_region,
-		struct badblocks *bb, const struct resource *res)
-{
-	struct nvdimm_bus *nvdimm_bus;
-	struct list_head *poison_list;
-
-	if (!is_memory(&nd_region->dev)) {
-		dev_WARN_ONCE(&nd_region->dev, 1,
-				"%s only valid for pmem regions\n", __func__);
-		return;
-	}
-	nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
-	poison_list = &nvdimm_bus->poison_list;
-
-	nvdimm_bus_lock(&nvdimm_bus->dev);
-	badblocks_populate(poison_list, bb, res);
-	nvdimm_bus_unlock(&nvdimm_bus->dev);
-}
-EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);
-
-static void append_poison_entry(struct nvdimm_bus *nvdimm_bus,
-		struct nd_poison *pl, u64 addr, u64 length)
-{
-	lockdep_assert_held(&nvdimm_bus->poison_lock);
-	pl->start = addr;
-	pl->length = length;
-	list_add_tail(&pl->list, &nvdimm_bus->poison_list);
-}
-
-static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length,
-			gfp_t flags)
-{
-	struct nd_poison *pl;
-
-	pl = kzalloc(sizeof(*pl), flags);
-	if (!pl)
-		return -ENOMEM;
-
-	append_poison_entry(nvdimm_bus, pl, addr, length);
-	return 0;
-}
-
-static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
-{
-	struct nd_poison *pl, *pl_new;
-
-	spin_unlock(&nvdimm_bus->poison_lock);
-	pl_new = kzalloc(sizeof(*pl_new), GFP_KERNEL);
-	spin_lock(&nvdimm_bus->poison_lock);
-
-	if (list_empty(&nvdimm_bus->poison_list)) {
-		if (!pl_new)
-			return -ENOMEM;
-		append_poison_entry(nvdimm_bus, pl_new, addr, length);
-		return 0;
-	}
-
-	/*
-	 * There is a chance this is a duplicate, check for those first.
-	 * This will be the common case as ARS_STATUS returns all known
-	 * errors in the SPA space, and we can't query it per region
-	 */
-	list_for_each_entry(pl, &nvdimm_bus->poison_list, list)
-		if (pl->start == addr) {
-			/* If length has changed, update this list entry */
-			if (pl->length != length)
-				pl->length = length;
-			kfree(pl_new);
-			return 0;
-		}
-
-	/*
-	 * If not a duplicate or a simple length update, add the entry as is,
-	 * as any overlapping ranges will get resolved when the list is consumed
-	 * and converted to badblocks
-	 */
-	if (!pl_new)
-		return -ENOMEM;
-	append_poison_entry(nvdimm_bus, pl_new, addr, length);
-
-	return 0;
-}
-
-int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
-{
-	int rc;
-
-	spin_lock(&nvdimm_bus->poison_lock);
-	rc = bus_add_poison(nvdimm_bus, addr, length);
-	spin_unlock(&nvdimm_bus->poison_lock);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);
-
-void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus, phys_addr_t start,
-		unsigned int len)
-{
-	struct list_head *poison_list = &nvdimm_bus->poison_list;
-	u64 clr_end = start + len - 1;
-	struct nd_poison *pl, *next;
-
-	spin_lock(&nvdimm_bus->poison_lock);
-	WARN_ON_ONCE(list_empty(poison_list));
-
-	/*
-	 * [start, clr_end] is the poison interval being cleared.
-	 * [pl->start, pl_end] is the poison_list entry we're comparing
-	 * the above interval against. The poison list entry may need
-	 * to be modified (update either start or length), deleted, or
-	 * split into two based on the overlap characteristics
-	 */
-
-	list_for_each_entry_safe(pl, next, poison_list, list) {
-		u64 pl_end = pl->start + pl->length - 1;
-
-		/* Skip intervals with no intersection */
-		if (pl_end < start)
-			continue;
-		if (pl->start >  clr_end)
-			continue;
-		/* Delete completely overlapped poison entries */
-		if ((pl->start >= start) && (pl_end <= clr_end)) {
-			list_del(&pl->list);
-			kfree(pl);
-			continue;
-		}
-		/* Adjust start point of partially cleared entries */
-		if ((start <= pl->start) && (clr_end > pl->start)) {
-			pl->length -= clr_end - pl->start + 1;
-			pl->start = clr_end + 1;
-			continue;
-		}
-		/* Adjust pl->length for partial clearing at the tail end */
-		if ((pl->start < start) && (pl_end <= clr_end)) {
-			/* pl->start remains the same */
-			pl->length = start - pl->start;
-			continue;
-		}
-		/*
-		 * If clearing in the middle of an entry, we split it into
-		 * two by modifying the current entry to represent one half of
-		 * the split, and adding a new entry for the second half.
-		 */
-		if ((pl->start < start) && (pl_end > clr_end)) {
-			u64 new_start = clr_end + 1;
-			u64 new_len = pl_end - new_start + 1;
-
-			/* Add new entry covering the right half */
-			add_poison(nvdimm_bus, new_start, new_len, GFP_NOWAIT);
-			/* Adjust this entry to cover the left half */
-			pl->length = start - pl->start;
-			continue;
-		}
-	}
-	spin_unlock(&nvdimm_bus->poison_lock);
-}
-EXPORT_SYMBOL_GPL(nvdimm_forget_poison);
+EXPORT_SYMBOL_GPL(nvdimm_bus_add_badrange);
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 86bc19ae30da..79274ead54fb 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -29,10 +29,9 @@ struct nvdimm_bus {
 	struct list_head list;
 	struct device dev;
 	int id, probe_active;
-	struct list_head poison_list;
 	struct list_head mapping_list;
 	struct mutex reconfig_mutex;
-	spinlock_t poison_lock;
+	struct badrange badrange;
 };
 
 struct nvdimm {
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 156be00e1f76..e958f3724c41 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -34,12 +34,6 @@ enum {
 	NVDIMM_IO_ATOMIC = 1,
 };
 
-struct nd_poison {
-	u64 start;
-	u64 length;
-	struct list_head list;
-};
-
 struct nvdimm_drvdata {
 	struct device *dev;
 	int nslabel_size;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 3eaad2fbf284..f8109ddb5ef1 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -18,6 +18,18 @@
 #include <linux/sizes.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
+#include <linux/spinlock.h>
+
+struct badrange_entry {
+	u64 start;
+	u64 length;
+	struct list_head list;
+};
+
+struct badrange {
+	struct list_head list;
+	spinlock_t lock;
+};
 
 enum {
 	/* when a dimm supports both PMEM and BLK access a label is required */
@@ -129,9 +141,12 @@ static inline struct nd_blk_region_desc *to_blk_region_desc(
 
 }
 
-int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length);
-void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus,
-		phys_addr_t start, unsigned int len);
+void badrange_init(struct badrange *badrange);
+int badrange_add(struct badrange *badrange, u64 addr, u64 length);
+void badrange_forget(struct badrange *badrange, phys_addr_t start,
+		unsigned int len);
+int nvdimm_bus_add_badrange(struct nvdimm_bus *nvdimm_bus, u64 addr,
+		u64 length);
 struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 		struct nvdimm_bus_descriptor *nfit_desc);
 void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index d870520da68b..3272ab5a5cb9 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -69,6 +69,7 @@ libnvdimm-y += $(NVDIMM_SRC)/region_devs.o
 libnvdimm-y += $(NVDIMM_SRC)/region.o
 libnvdimm-y += $(NVDIMM_SRC)/namespace_devs.o
 libnvdimm-y += $(NVDIMM_SRC)/label.o
+libnvdimm-y += $(NVDIMM_SRC)/badrange.o
 libnvdimm-$(CONFIG_ND_CLAIM) += $(NVDIMM_SRC)/claim.o
 libnvdimm-$(CONFIG_BTT) += $(NVDIMM_SRC)/btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += $(NVDIMM_SRC)/pfn_devs.o
-- 
cgit v1.2.3


From 9fb1a1903345fea598f48277576a3589a972b72e Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Mon, 30 Oct 2017 13:22:20 -0700
Subject: nfit_test: add error injection DSMs

Add nfit_test emulation for the new ACPI 6.2 error injectino DSMs.
This will allow unit tests to selectively inject the errors they wish to
test for.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
[vishal: Move injection functions to ND_CMD_CALL]
[vishal: Add support for the notification option]
[vishal: move an nfit_test private definition into a local header]
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c      | 187 +++++++++++++++++++++++++++++-----
 tools/testing/nvdimm/test/nfit_test.h |   5 +
 2 files changed, 168 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 3a3bad348d56..788b1a5d6c5a 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -168,8 +168,12 @@ struct nfit_test {
 		spinlock_t lock;
 	} ars_state;
 	struct device *dimm_dev[NUM_DCR];
+	struct badrange badrange;
+	struct work_struct work;
 };
 
+static struct workqueue_struct *nfit_wq;
+
 static struct nfit_test *to_nfit_test(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -234,48 +238,68 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd,
 	return rc;
 }
 
-#define NFIT_TEST_ARS_RECORDS 4
 #define NFIT_TEST_CLEAR_ERR_UNIT 256
 
 static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd,
 		unsigned int buf_len)
 {
+	int ars_recs;
+
 	if (buf_len < sizeof(*nd_cmd))
 		return -EINVAL;
 
+	/* for testing, only store up to n records that fit within 4k */
+	ars_recs = SZ_4K / sizeof(struct nd_ars_record);
+
 	nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status)
-		+ NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record);
+		+ ars_recs * sizeof(struct nd_ars_record);
 	nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16;
 	nd_cmd->clear_err_unit = NFIT_TEST_CLEAR_ERR_UNIT;
 
 	return 0;
 }
 
-/*
- * Initialize the ars_state to return an ars_result 1 second in the future with
- * a 4K error range in the middle of the requested address range.
- */
-static void post_ars_status(struct ars_state *ars_state, u64 addr, u64 len)
+static void post_ars_status(struct ars_state *ars_state,
+		struct badrange *badrange, u64 addr, u64 len)
 {
 	struct nd_cmd_ars_status *ars_status;
 	struct nd_ars_record *ars_record;
+	struct badrange_entry *be;
+	u64 end = addr + len - 1;
+	int i = 0;
 
 	ars_state->deadline = jiffies + 1*HZ;
 	ars_status = ars_state->ars_status;
 	ars_status->status = 0;
-	ars_status->out_length = sizeof(struct nd_cmd_ars_status)
-		+ sizeof(struct nd_ars_record);
 	ars_status->address = addr;
 	ars_status->length = len;
 	ars_status->type = ND_ARS_PERSISTENT;
-	ars_status->num_records = 1;
-	ars_record = &ars_status->records[0];
-	ars_record->handle = 0;
-	ars_record->err_address = addr + len / 2;
-	ars_record->length = SZ_4K;
+
+	spin_lock(&badrange->lock);
+	list_for_each_entry(be, &badrange->list, list) {
+		u64 be_end = be->start + be->length - 1;
+		u64 rstart, rend;
+
+		/* skip entries outside the range */
+		if (be_end < addr || be->start > end)
+			continue;
+
+		rstart = (be->start < addr) ? addr : be->start;
+		rend = (be_end < end) ? be_end : end;
+		ars_record = &ars_status->records[i];
+		ars_record->handle = 0;
+		ars_record->err_address = rstart;
+		ars_record->length = rend - rstart + 1;
+		i++;
+	}
+	spin_unlock(&badrange->lock);
+	ars_status->num_records = i;
+	ars_status->out_length = sizeof(struct nd_cmd_ars_status)
+		+ i * sizeof(struct nd_ars_record);
 }
 
-static int nfit_test_cmd_ars_start(struct ars_state *ars_state,
+static int nfit_test_cmd_ars_start(struct nfit_test *t,
+		struct ars_state *ars_state,
 		struct nd_cmd_ars_start *ars_start, unsigned int buf_len,
 		int *cmd_rc)
 {
@@ -289,7 +313,7 @@ static int nfit_test_cmd_ars_start(struct ars_state *ars_state,
 	} else {
 		ars_start->status = 0;
 		ars_start->scrub_time = 1;
-		post_ars_status(ars_state, ars_start->address,
+		post_ars_status(ars_state, &t->badrange, ars_start->address,
 				ars_start->length);
 		*cmd_rc = 0;
 	}
@@ -456,6 +480,93 @@ static int nfit_test_cmd_smart_threshold(struct nd_cmd_smart_threshold *smart_t,
 	return 0;
 }
 
+static void uc_error_notify(struct work_struct *work)
+{
+	struct nfit_test *t = container_of(work, typeof(*t), work);
+
+	__acpi_nfit_notify(&t->pdev.dev, t, NFIT_NOTIFY_UC_MEMORY_ERROR);
+}
+
+static int nfit_test_cmd_ars_error_inject(struct nfit_test *t,
+		struct nd_cmd_ars_err_inj *err_inj, unsigned int buf_len)
+{
+	int rc;
+
+	if (buf_len < sizeof(*err_inj)) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	if (err_inj->err_inj_spa_range_length <= 0) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	rc =  badrange_add(&t->badrange, err_inj->err_inj_spa_range_base,
+			err_inj->err_inj_spa_range_length);
+	if (rc < 0)
+		goto err;
+
+	if (err_inj->err_inj_options & (1 << ND_ARS_ERR_INJ_OPT_NOTIFY))
+		queue_work(nfit_wq, &t->work);
+
+	err_inj->status = 0;
+	return 0;
+
+err:
+	err_inj->status = NFIT_ARS_INJECT_INVALID;
+	return rc;
+}
+
+static int nfit_test_cmd_ars_inject_clear(struct nfit_test *t,
+		struct nd_cmd_ars_err_inj_clr *err_clr, unsigned int buf_len)
+{
+	int rc;
+
+	if (buf_len < sizeof(*err_clr)) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	if (err_clr->err_inj_clr_spa_range_length <= 0) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	badrange_forget(&t->badrange, err_clr->err_inj_clr_spa_range_base,
+			err_clr->err_inj_clr_spa_range_length);
+
+	err_clr->status = 0;
+	return 0;
+
+err:
+	err_clr->status = NFIT_ARS_INJECT_INVALID;
+	return rc;
+}
+
+static int nfit_test_cmd_ars_inject_status(struct nfit_test *t,
+		struct nd_cmd_ars_err_inj_stat *err_stat,
+		unsigned int buf_len)
+{
+	struct badrange_entry *be;
+	int max = SZ_4K / sizeof(struct nd_error_stat_query_record);
+	int i = 0;
+
+	err_stat->status = 0;
+	spin_lock(&t->badrange.lock);
+	list_for_each_entry(be, &t->badrange.list, list) {
+		err_stat->record[i].err_inj_stat_spa_range_base = be->start;
+		err_stat->record[i].err_inj_stat_spa_range_length = be->length;
+		i++;
+		if (i > max)
+			break;
+	}
+	spin_unlock(&t->badrange.lock);
+	err_stat->inj_err_rec_count = i;
+
+	return 0;
+}
+
 static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc)
@@ -543,6 +654,18 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 				rc = nfit_test_cmd_translate_spa(
 					acpi_desc->nvdimm_bus, buf, buf_len);
 				return rc;
+			case NFIT_CMD_ARS_INJECT_SET:
+				rc = nfit_test_cmd_ars_error_inject(t, buf,
+					buf_len);
+				return rc;
+			case NFIT_CMD_ARS_INJECT_CLEAR:
+				rc = nfit_test_cmd_ars_inject_clear(t, buf,
+					buf_len);
+				return rc;
+			case NFIT_CMD_ARS_INJECT_GET:
+				rc = nfit_test_cmd_ars_inject_status(t, buf,
+					buf_len);
+				return rc;
 			default:
 				return -ENOTTY;
 			}
@@ -556,8 +679,8 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			rc = nfit_test_cmd_ars_cap(buf, buf_len);
 			break;
 		case ND_CMD_ARS_START:
-			rc = nfit_test_cmd_ars_start(ars_state, buf, buf_len,
-					cmd_rc);
+			rc = nfit_test_cmd_ars_start(t, ars_state, buf,
+					buf_len, cmd_rc);
 			break;
 		case ND_CMD_ARS_STATUS:
 			rc = nfit_test_cmd_ars_status(ars_state, buf, buf_len,
@@ -664,10 +787,9 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 
 static int ars_state_init(struct device *dev, struct ars_state *ars_state)
 {
+	/* for testing, only store up to n records that fit within 4k */
 	ars_state->ars_status = devm_kzalloc(dev,
-			sizeof(struct nd_cmd_ars_status)
-			+ sizeof(struct nd_ars_record) * NFIT_TEST_ARS_RECORDS,
-			GFP_KERNEL);
+			sizeof(struct nd_cmd_ars_status) + SZ_4K, GFP_KERNEL);
 	if (!ars_state->ars_status)
 		return -ENOMEM;
 	spin_lock_init(&ars_state->lock);
@@ -1517,7 +1639,8 @@ static void nfit_test0_setup(struct nfit_test *t)
 				+ i * sizeof(u64);
 	}
 
-	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE);
+	post_ars_status(&t->ars_state, &t->badrange, t->spa_set_dma[0],
+			SPA0_SIZE);
 
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
@@ -1531,6 +1654,9 @@ static void nfit_test0_setup(struct nfit_test *t)
 	set_bit(ND_CMD_CALL, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_SMART_THRESHOLD, &acpi_desc->dimm_cmd_force_en);
 	set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_nfit_cmd_force_en);
+	set_bit(NFIT_CMD_ARS_INJECT_SET, &acpi_desc->bus_nfit_cmd_force_en);
+	set_bit(NFIT_CMD_ARS_INJECT_CLEAR, &acpi_desc->bus_nfit_cmd_force_en);
+	set_bit(NFIT_CMD_ARS_INJECT_GET, &acpi_desc->bus_nfit_cmd_force_en);
 }
 
 static void nfit_test1_setup(struct nfit_test *t)
@@ -1620,7 +1746,8 @@ static void nfit_test1_setup(struct nfit_test *t)
 	dcr->code = NFIT_FIC_BYTE;
 	dcr->windows = 0;
 
-	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA2_SIZE);
+	post_ars_status(&t->ars_state, &t->badrange, t->spa_set_dma[0],
+			SPA2_SIZE);
 
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_cmd_force_en);
@@ -1718,7 +1845,10 @@ static int nfit_ctl_test(struct device *dev)
 			.module = THIS_MODULE,
 			.provider_name = "ACPI.NFIT",
 			.ndctl = acpi_nfit_ctl,
-			.bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA,
+			.bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA
+				| 1UL << NFIT_CMD_ARS_INJECT_SET
+				| 1UL << NFIT_CMD_ARS_INJECT_CLEAR
+				| 1UL << NFIT_CMD_ARS_INJECT_GET,
 		},
 		.dev = &adev->dev,
 	};
@@ -2017,6 +2147,10 @@ static __init int nfit_test_init(void)
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);
 
+	nfit_wq = create_singlethread_workqueue("nfit");
+	if (!nfit_wq)
+		return -ENOMEM;
+
 	nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm");
 	if (IS_ERR(nfit_test_dimm)) {
 		rc = PTR_ERR(nfit_test_dimm);
@@ -2033,6 +2167,7 @@ static __init int nfit_test_init(void)
 			goto err_register;
 		}
 		INIT_LIST_HEAD(&nfit_test->resources);
+		badrange_init(&nfit_test->badrange);
 		switch (i) {
 		case 0:
 			nfit_test->num_pm = NUM_PM;
@@ -2068,6 +2203,7 @@ static __init int nfit_test_init(void)
 			goto err_register;
 
 		instances[i] = nfit_test;
+		INIT_WORK(&nfit_test->work, uc_error_notify);
 	}
 
 	rc = platform_driver_register(&nfit_test_driver);
@@ -2076,6 +2212,7 @@ static __init int nfit_test_init(void)
 	return 0;
 
  err_register:
+	destroy_workqueue(nfit_wq);
 	for (i = 0; i < NUM_NFITS; i++)
 		if (instances[i])
 			platform_device_unregister(&instances[i]->pdev);
@@ -2091,6 +2228,8 @@ static __exit void nfit_test_exit(void)
 {
 	int i;
 
+	flush_workqueue(nfit_wq);
+	destroy_workqueue(nfit_wq);
 	for (i = 0; i < NUM_NFITS; i++)
 		platform_device_unregister(&instances[i]->pdev);
 	platform_driver_unregister(&nfit_test_driver);
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index 52c83be9dcfa..113b44675a71 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -33,6 +33,11 @@ struct nfit_test_resource {
 };
 
 #define ND_TRANSLATE_SPA_STATUS_INVALID_SPA  2
+#define NFIT_ARS_INJECT_INVALID 2
+
+enum err_inj_options {
+	ND_ARS_ERR_INJ_OPT_NOTIFY = 0,
+};
 
 /* nfit commands */
 enum nfit_cmd_num {
-- 
cgit v1.2.3


From 5e096ef3b29e6113a7aa6a7dc4871987efa99bcb Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Mon, 30 Oct 2017 13:22:23 -0700
Subject: nfit_test: when clearing poison, also remove badrange entries

The injected badrange entries can only be cleared from the kernel's
accounting by writing to the affected blocks, so when such a write sends
the clear errror DSM to nfit_test, also clear the ranges from
nfit_test's badrange list. This lets an 'ARS Inject error status' DSM to
return the correct status, omitting the cleared ranges.

Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 788b1a5d6c5a..79c5cb23693f 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -344,7 +344,8 @@ static int nfit_test_cmd_ars_status(struct ars_state *ars_state,
 	return 0;
 }
 
-static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
+static int nfit_test_cmd_clear_error(struct nfit_test *t,
+		struct nd_cmd_clear_error *clear_err,
 		unsigned int buf_len, int *cmd_rc)
 {
 	const u64 mask = NFIT_TEST_CLEAR_ERR_UNIT - 1;
@@ -354,12 +355,7 @@ static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
 	if ((clear_err->address & mask) || (clear_err->length & mask))
 		return -EINVAL;
 
-	/*
-	 * Report 'all clear' success for all commands even though a new
-	 * scrub will find errors again.  This is enough to have the
-	 * error removed from the 'badblocks' tracking in the pmem
-	 * driver.
-	 */
+	badrange_forget(&t->badrange, clear_err->address, clear_err->length);
 	clear_err->status = 0;
 	clear_err->cleared = clear_err->length;
 	*cmd_rc = 0;
@@ -687,7 +683,7 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 					cmd_rc);
 			break;
 		case ND_CMD_CLEAR_ERROR:
-			rc = nfit_test_cmd_clear_error(buf, buf_len, cmd_rc);
+			rc = nfit_test_cmd_clear_error(t, buf, buf_len, cmd_rc);
 			break;
 		default:
 			return -ENOTTY;
-- 
cgit v1.2.3


From 1c9725974074a047f6080eecc62c50a8e840d050 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 1 Nov 2017 16:36:30 +0100
Subject: mm: introduce MAP_SHARED_VALIDATE, a mechanism to safely define new
 mmap flags

The mmap(2) syscall suffers from the ABI anti-pattern of not validating
unknown flags. However, proposals like MAP_SYNC need a mechanism to
define new behavior that is known to fail on older kernels without the
support. Define a new MAP_SHARED_VALIDATE flag pattern that is
guaranteed to fail on all legacy mmap implementations.

It is worth noting that the original proposal was for a standalone
MAP_VALIDATE flag. However, when that  could not be supported by all
archs Linus observed:

    I see why you *think* you want a bitmap. You think you want
    a bitmap because you want to make MAP_VALIDATE be part of MAP_SYNC
    etc, so that people can do

    ret = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED
		    | MAP_SYNC, fd, 0);

    and "know" that MAP_SYNC actually takes.

    And I'm saying that whole wish is bogus. You're fundamentally
    depending on special semantics, just make it explicit. It's already
    not portable, so don't try to make it so.

    Rename that MAP_VALIDATE as MAP_SHARED_VALIDATE, make it have a value
    of 0x3, and make people do

    ret = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED_VALIDATE
		    | MAP_SYNC, fd, 0);

    and then the kernel side is easier too (none of that random garbage
    playing games with looking at the "MAP_VALIDATE bit", but just another
    case statement in that map type thing.

    Boom. Done.

Similar to ->fallocate() we also want the ability to validate the
support for new flags on a per ->mmap() 'struct file_operations'
instance basis.  Towards that end arrange for flags to be generically
validated against a mmap_supported_flags exported by 'struct
file_operations'. By default all existing flags are implicitly
supported, but new flags require MAP_SHARED_VALIDATE and
per-instance-opt-in.

Cc: Jan Kara <jack@suse.cz>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Suggested-by: Christoph Hellwig <hch@lst.de>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/alpha/include/uapi/asm/mman.h           |  1 +
 arch/mips/include/uapi/asm/mman.h            |  1 +
 arch/parisc/include/uapi/asm/mman.h          |  1 +
 arch/xtensa/include/uapi/asm/mman.h          |  1 +
 include/linux/fs.h                           |  1 +
 include/linux/mman.h                         | 39 ++++++++++++++++++++++++++++
 include/uapi/asm-generic/mman-common.h       |  1 +
 mm/mmap.c                                    | 15 +++++++++++
 tools/include/uapi/asm-generic/mman-common.h |  1 +
 9 files changed, 61 insertions(+)

(limited to 'tools')

diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 3b26cc62dadb..f6d118aaedb9 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -11,6 +11,7 @@
 
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
 #define MAP_TYPE	0x0f		/* Mask for type of mapping (OSF/1 is _wrong_) */
 #define MAP_FIXED	0x100		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x10		/* don't use a file */
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index da3216007fe0..93268e4cd3c7 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -28,6 +28,7 @@
  */
 #define MAP_SHARED	0x001		/* Share changes */
 #define MAP_PRIVATE	0x002		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x003	/* share + validate extension flags */
 #define MAP_TYPE	0x00f		/* Mask for type of mapping */
 #define MAP_FIXED	0x010		/* Interpret addr exactly */
 
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 775b5d5e41a1..bca652aa1677 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -11,6 +11,7 @@
 
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
 #define MAP_TYPE	0x03		/* Mask for type of mapping */
 #define MAP_FIXED	0x04		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x10		/* don't use a file */
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index b15b278aa314..9ab426374714 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -35,6 +35,7 @@
  */
 #define MAP_SHARED	0x001		/* Share changes */
 #define MAP_PRIVATE	0x002		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x003	/* share + validate extension flags */
 #define MAP_TYPE	0x00f		/* Mask for type of mapping */
 #define MAP_FIXED	0x010		/* Interpret addr exactly */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 13dab191a23e..57added3201d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1701,6 +1701,7 @@ struct file_operations {
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
+	unsigned long mmap_supported_flags;
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
diff --git a/include/linux/mman.h b/include/linux/mman.h
index edb6cf6a81ed..74452e3f2536 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -7,6 +7,45 @@
 #include <linux/atomic.h>
 #include <uapi/linux/mman.h>
 
+/*
+ * Arrange for legacy / undefined architecture specific flags to be
+ * ignored by default in LEGACY_MAP_MASK.
+ */
+#ifndef MAP_32BIT
+#define MAP_32BIT 0
+#endif
+#ifndef MAP_HUGE_2MB
+#define MAP_HUGE_2MB 0
+#endif
+#ifndef MAP_HUGE_1GB
+#define MAP_HUGE_1GB 0
+#endif
+#ifndef MAP_UNINITIALIZED
+#define MAP_UNINITIALIZED 0
+#endif
+
+/*
+ * The historical set of flags that all mmap implementations implicitly
+ * support when a ->mmap_validate() op is not provided in file_operations.
+ */
+#define LEGACY_MAP_MASK (MAP_SHARED \
+		| MAP_PRIVATE \
+		| MAP_FIXED \
+		| MAP_ANONYMOUS \
+		| MAP_DENYWRITE \
+		| MAP_EXECUTABLE \
+		| MAP_UNINITIALIZED \
+		| MAP_GROWSDOWN \
+		| MAP_LOCKED \
+		| MAP_NORESERVE \
+		| MAP_POPULATE \
+		| MAP_NONBLOCK \
+		| MAP_STACK \
+		| MAP_HUGETLB \
+		| MAP_32BIT \
+		| MAP_HUGE_2MB \
+		| MAP_HUGE_1GB)
+
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern unsigned long sysctl_overcommit_kbytes;
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index 203268f9231e..8ce7f5a0800f 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -16,6 +16,7 @@
 
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
 #define MAP_TYPE	0x0f		/* Mask for type of mapping */
 #define MAP_FIXED	0x10		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x20		/* don't use a file */
diff --git a/mm/mmap.c b/mm/mmap.c
index 680506faceae..924839fac0e6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1387,9 +1387,24 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 
 	if (file) {
 		struct inode *inode = file_inode(file);
+		unsigned long flags_mask;
+
+		flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
 
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
+			/*
+			 * Force use of MAP_SHARED_VALIDATE with non-legacy
+			 * flags. E.g. MAP_SYNC is dangerous to use with
+			 * MAP_SHARED as you don't know which consistency model
+			 * you will get. We silently ignore unsupported flags
+			 * with MAP_SHARED to preserve backward compatibility.
+			 */
+			flags &= LEGACY_MAP_MASK;
+			/* fall through */
+		case MAP_SHARED_VALIDATE:
+			if (flags & ~flags_mask)
+				return -EOPNOTSUPP;
 			if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
 				return -EACCES;
 
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 203268f9231e..8ce7f5a0800f 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -16,6 +16,7 @@
 
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
 #define MAP_TYPE	0x0f		/* Mask for type of mapping */
 #define MAP_FIXED	0x10		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x20		/* don't use a file */
-- 
cgit v1.2.3


From 9da779c324db87ca340e0eb1259c949874f17bed Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Wed, 25 Oct 2017 09:51:32 -0400
Subject: cpupower: Fix no-rounding MHz frequency output

'cpupower frequency-info -ln' returns kHz values on systems with MHz range
minimum CPU frequency range.  For example, on a 800MHz to 4.20GHz system
the command returns

hardware limits: 800000 MHz - 4.200000 GHz

The code that causes this error can be removed.  The next else if clause
will handle the output correctly such that

hardware limits: 800.000 MHz - 4.200000 GHz

is displayed correctly.

[v2]: Remove two lines instead of fixing broken code.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Renninger <trenn@suse.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Reviewed-by: Stafford Horne <shorne@gmail.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/power/cpupower/utils/cpufreq-info.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index 3e701f0e9c14..df43cd45d810 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -93,8 +93,6 @@ static void print_speed(unsigned long speed)
 		if (speed > 1000000)
 			printf("%u.%06u GHz", ((unsigned int) speed/1000000),
 				((unsigned int) speed%1000000));
-		else if (speed > 100000)
-			printf("%u MHz", (unsigned int) speed);
 		else if (speed > 1000)
 			printf("%u.%03u MHz", ((unsigned int) speed/1000),
 				(unsigned int) (speed%1000));
-- 
cgit v1.2.3


From 9d64fc08f6fe59a7d71e84f650dd2c0f080254dd Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@dell.com>
Date: Wed, 1 Nov 2017 14:25:37 -0500
Subject: tools/wmi: add a sample for dell smbios communication over WMI

This application uses the character device /dev/wmi/dell-smbios
to perform SMBIOS communications from userspace.

It offers demonstrations of a few simple tasks:
 - Running a class/select command
 - Querying a token value
 - Activating a token

Signed-off-by: Mario Limonciello <mario.limonciello@dell.com>
Reviewed-by: Edward O'Callaghan <quasisec@google.com>
Signed-off-by: Darren Hart (VMware) <dvhart@infradead.org>
---
 MAINTAINERS                     |   1 +
 tools/Makefile                  |  14 +--
 tools/wmi/Makefile              |  18 ++++
 tools/wmi/dell-smbios-example.c | 210 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 237 insertions(+), 6 deletions(-)
 create mode 100644 tools/wmi/Makefile
 create mode 100644 tools/wmi/dell-smbios-example.c

(limited to 'tools')

diff --git a/MAINTAINERS b/MAINTAINERS
index 3af07502220a..da1851fc88a5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3997,6 +3997,7 @@ M:	Mario Limonciello <mario.limonciello@dell.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/dell-smbios-wmi.c
+F:	tools/wmi/dell-smbios-example.c
 
 DELL LAPTOP DRIVER
 M:	Matthew Garrett <mjg59@srcf.ucam.org>
diff --git a/tools/Makefile b/tools/Makefile
index 9dfede37c8ff..9d2fd2606810 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -29,6 +29,7 @@ help:
 	@echo '  usb                    - USB testing tools'
 	@echo '  virtio                 - vhost test module'
 	@echo '  vm                     - misc vm tools'
+	@echo '  wmi			- WMI interface examples'
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
 	@echo ''
 	@echo 'You can do:'
@@ -57,7 +58,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds: FORCE
+cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds wmi: FORCE
 	$(call descend,$@)
 
 liblockdep: FORCE
@@ -92,7 +93,7 @@ kvm_stat: FORCE
 all: acpi cgroup cpupower gpio hv firewire liblockdep \
 		perf selftests spi turbostat usb \
 		virtio vm net x86_energy_perf_policy \
-		tmon freefall iio objtool kvm_stat
+		tmon freefall iio objtool kvm_stat wmi
 
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
@@ -100,7 +101,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install net_install objtool_install:
+cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install net_install objtool_install wmi_install:
 	$(call descend,$(@:_install=),install)
 
 liblockdep_install:
@@ -125,7 +126,8 @@ install: acpi_install cgroup_install cpupower_install gpio_install \
 		hv_install firewire_install iio_install liblockdep_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install vm_install net_install x86_energy_perf_policy_install \
-		tmon_install freefall_install objtool_install kvm_stat_install
+		tmon_install freefall_install objtool_install kvm_stat_install \
+		wmi_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
@@ -133,7 +135,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean:
+cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean net_clean iio_clean gpio_clean objtool_clean leds_clean:
 	$(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -171,6 +173,6 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
 		vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
-		gpio_clean objtool_clean leds_clean
+		gpio_clean objtool_clean leds_clean wmi_clean
 
 .PHONY: FORCE
diff --git a/tools/wmi/Makefile b/tools/wmi/Makefile
new file mode 100644
index 000000000000..e664f1167388
--- /dev/null
+++ b/tools/wmi/Makefile
@@ -0,0 +1,18 @@
+PREFIX ?= /usr
+SBINDIR ?= sbin
+INSTALL ?= install
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+CC = $(CROSS_COMPILE)gcc
+
+TARGET = dell-smbios-example
+
+all: $(TARGET)
+
+%: %.c
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $<
+
+clean:
+	$(RM) $(TARGET)
+
+install: dell-smbios-example
+	$(INSTALL) -D -m 755 $(TARGET) $(DESTDIR)$(PREFIX)/$(SBINDIR)/$(TARGET)
diff --git a/tools/wmi/dell-smbios-example.c b/tools/wmi/dell-smbios-example.c
new file mode 100644
index 000000000000..9d3bde081249
--- /dev/null
+++ b/tools/wmi/dell-smbios-example.c
@@ -0,0 +1,210 @@
+/*
+ *  Sample application for SMBIOS communication over WMI interface
+ *  Performs the following:
+ *  - Simple cmd_class/cmd_select lookup for TPM information
+ *  - Simple query of known tokens and their values
+ *  - Simple activation of a token
+ *
+ *  Copyright (C) 2017 Dell, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+/* if uapi header isn't installed, this might not yet exist */
+#ifndef __packed
+#define __packed __attribute__((packed))
+#endif
+#include <linux/wmi.h>
+
+/* It would be better to discover these using udev, but for a simple
+ * application they're hardcoded
+ */
+static const char *ioctl_devfs = "/dev/wmi/dell-smbios";
+static const char *token_sysfs =
+			"/sys/bus/platform/devices/dell-smbios.0/tokens";
+
+static void show_buffer(struct dell_wmi_smbios_buffer *buffer)
+{
+	printf("Call: %x/%x [%x,%x,%x,%x]\nResults: [%8x,%8x,%8x,%8x]\n",
+	buffer->std.cmd_class, buffer->std.cmd_select,
+	buffer->std.input[0], buffer->std.input[1],
+	buffer->std.input[2], buffer->std.input[3],
+	buffer->std.output[0], buffer->std.output[1],
+	buffer->std.output[2], buffer->std.output[3]);
+}
+
+static int run_wmi_smbios_cmd(struct dell_wmi_smbios_buffer *buffer)
+{
+	int fd;
+	int ret;
+
+	fd = open(ioctl_devfs, O_NONBLOCK);
+	ret = ioctl(fd, DELL_WMI_SMBIOS_CMD, buffer);
+	close(fd);
+	return ret;
+}
+
+static int find_token(__u16 token, __u16 *location, __u16 *value)
+{
+	char location_sysfs[60];
+	char value_sysfs[57];
+	char buf[4096];
+	FILE *f;
+	int ret;
+
+	ret = sprintf(value_sysfs, "%s/%04x_value", token_sysfs, token);
+	if (ret < 0) {
+		printf("sprintf value failed\n");
+		return 2;
+	}
+	f = fopen(value_sysfs, "rb");
+	if (!f) {
+		printf("failed to open %s\n", value_sysfs);
+		return 2;
+	}
+	fread(buf, 1, 4096, f);
+	fclose(f);
+	*value = (__u16) strtol(buf, NULL, 16);
+
+	ret = sprintf(location_sysfs, "%s/%04x_location", token_sysfs, token);
+	if (ret < 0) {
+		printf("sprintf location failed\n");
+		return 1;
+	}
+	f = fopen(location_sysfs, "rb");
+	if (!f) {
+		printf("failed to open %s\n", location_sysfs);
+		return 2;
+	}
+	fread(buf, 1, 4096, f);
+	fclose(f);
+	*location = (__u16) strtol(buf, NULL, 16);
+
+	if (*location)
+		return 0;
+	return 2;
+}
+
+static int token_is_active(__u16 *location, __u16 *cmpvalue,
+			   struct dell_wmi_smbios_buffer *buffer)
+{
+	int ret;
+
+	buffer->std.cmd_class = CLASS_TOKEN_READ;
+	buffer->std.cmd_select = SELECT_TOKEN_STD;
+	buffer->std.input[0] = *location;
+	ret = run_wmi_smbios_cmd(buffer);
+	if (ret != 0 || buffer->std.output[0] != 0)
+		return ret;
+	ret = (buffer->std.output[1] == *cmpvalue);
+	return ret;
+}
+
+static int query_token(__u16 token, struct dell_wmi_smbios_buffer *buffer)
+{
+	__u16 location;
+	__u16 value;
+	int ret;
+
+	ret = find_token(token, &location, &value);
+	if (ret != 0) {
+		printf("unable to find token %04x\n", token);
+		return 1;
+	}
+	return token_is_active(&location, &value, buffer);
+}
+
+static int activate_token(struct dell_wmi_smbios_buffer *buffer,
+		   __u16 token)
+{
+	__u16 location;
+	__u16 value;
+	int ret;
+
+	ret = find_token(token, &location, &value);
+	if (ret != 0) {
+		printf("unable to find token %04x\n", token);
+		return 1;
+	}
+	buffer->std.cmd_class = CLASS_TOKEN_WRITE;
+	buffer->std.cmd_select = SELECT_TOKEN_STD;
+	buffer->std.input[0] = location;
+	buffer->std.input[1] = 1;
+	ret = run_wmi_smbios_cmd(buffer);
+	return ret;
+}
+
+static int query_buffer_size(__u64 *buffer_size)
+{
+	FILE *f;
+
+	f = fopen(ioctl_devfs, "rb");
+	if (!f)
+		return -EINVAL;
+	fread(buffer_size, sizeof(__u64), 1, f);
+	fclose(f);
+	return EXIT_SUCCESS;
+}
+
+int main(void)
+{
+	struct dell_wmi_smbios_buffer *buffer;
+	int ret;
+	__u64 value = 0;
+
+	ret = query_buffer_size(&value);
+	if (ret == EXIT_FAILURE || !value) {
+		printf("Unable to read buffer size\n");
+		goto out;
+	}
+	printf("Detected required buffer size %lld\n", value);
+
+	buffer = malloc(value);
+	if (buffer == NULL) {
+		printf("failed to alloc memory for ioctl\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+	buffer->length = value;
+
+	/* simple SMBIOS call for looking up TPM info */
+	buffer->std.cmd_class = CLASS_FLASH_INTERFACE;
+	buffer->std.cmd_select = SELECT_FLASH_INTERFACE;
+	buffer->std.input[0] = 2;
+	ret = run_wmi_smbios_cmd(buffer);
+	if (ret) {
+		printf("smbios ioctl failed: %d\n", ret);
+		ret = EXIT_FAILURE;
+		goto out;
+	}
+	show_buffer(buffer);
+
+	/* query some tokens */
+	ret = query_token(CAPSULE_EN_TOKEN, buffer);
+	printf("UEFI Capsule enabled token is: %d\n", ret);
+	ret = query_token(CAPSULE_DIS_TOKEN, buffer);
+	printf("UEFI Capsule disabled token is: %d\n", ret);
+
+	/* activate UEFI capsule token if disabled */
+	if (ret) {
+		printf("Enabling UEFI capsule token");
+		if (activate_token(buffer, CAPSULE_EN_TOKEN)) {
+			printf("activate failed\n");
+			ret = -1;
+			goto out;
+		}
+	}
+	ret = EXIT_SUCCESS;
+out:
+	free(buffer);
+	return ret;
+}
-- 
cgit v1.2.3


From 928631e05495fa1f0e9775f555b94dbcbb4e2fb5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 3 Nov 2017 13:56:19 -0700
Subject: bpftool: print program device bound info

If program is bound to a device, print the name of the relevant
interface or unknown if the netdev has since been removed.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/prog.c       | 31 +++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 2 files changed, 38 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 250f80fd46aa..d3ab808dc882 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -41,6 +41,7 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
+#include <net/if.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
@@ -229,6 +230,21 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 		     info->tag[0], info->tag[1], info->tag[2], info->tag[3],
 		     info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
 
+	if (info->status & BPF_PROG_STATUS_DEV_BOUND) {
+		jsonw_name(json_wtr, "dev");
+		if (info->ifindex) {
+			char name[IF_NAMESIZE];
+
+			if (!if_indextoname(info->ifindex, name))
+				jsonw_printf(json_wtr, "\"ifindex:%d\"",
+					     info->ifindex);
+			else
+				jsonw_printf(json_wtr, "\"%s\"", name);
+		} else {
+			jsonw_printf(json_wtr, "\"unknown\"");
+		}
+	}
+
 	if (info->load_time) {
 		char buf[32];
 
@@ -274,6 +290,21 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 
 	printf("tag ");
 	fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
+	printf(" ");
+
+	if (info->status & BPF_PROG_STATUS_DEV_BOUND) {
+		printf("dev ");
+		if (info->ifindex) {
+			char name[IF_NAMESIZE];
+
+			if (!if_indextoname(info->ifindex, name))
+				printf("ifindex:%d ", info->ifindex);
+			else
+				printf("%s ", name);
+		} else {
+			printf("unknown ");
+		}
+	}
 	printf("\n");
 
 	if (info->load_time) {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7cebba491011..e92f62cf933a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -259,6 +259,7 @@ union bpf_attr {
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
+		__u32		prog_target_ifindex;	/* ifindex of netdev to prep for */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -893,6 +894,10 @@ enum sk_action {
 
 #define BPF_TAG_SIZE	8
 
+enum bpf_prog_status {
+	BPF_PROG_STATUS_DEV_BOUND	= (1 << 0),
+};
+
 struct bpf_prog_info {
 	__u32 type;
 	__u32 id;
@@ -906,6 +911,8 @@ struct bpf_prog_info {
 	__u32 nr_map_ids;
 	__aligned_u64 map_ids;
 	char name[BPF_OBJ_NAME_LEN];
+	__u32 ifindex;
+	__u32 status;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
-- 
cgit v1.2.3


From 0b1c27db12fd338ed912fec18f5cc02d7bd4e54e Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 3 Nov 2017 13:59:07 -0700
Subject: tools: bpftool: move p_err() and p_info() from main.h to common.c

The two functions were declared as static inline in a header file. There
is no particular reason why they should be inlined, they just happened to
remain in the same header file when they were turned from macros to
functions in a precious commit.

Make them non-inlined functions and move them to common.c file instead.

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/common.c | 31 +++++++++++++++++++++++++++++++
 tools/bpf/bpftool/main.h   | 34 +++-------------------------------
 2 files changed, 34 insertions(+), 31 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index f0288269dae8..aa7017098b2a 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -50,6 +50,37 @@
 
 #include "main.h"
 
+void p_err(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "error");
+		jsonw_vprintf_enquote(json_wtr, fmt, ap);
+		jsonw_end_object(json_wtr);
+	} else {
+		fprintf(stderr, "Error: ");
+		vfprintf(stderr, fmt, ap);
+		fprintf(stderr, "\n");
+	}
+	va_end(ap);
+}
+
+void p_info(const char *fmt, ...)
+{
+	va_list ap;
+
+	if (json_output)
+		return;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	fprintf(stderr, "\n");
+	va_end(ap);
+}
+
 static bool is_bpffs(char *path)
 {
 	struct statfs st_fs;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d315d01be645..ff5ad05b137b 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -71,6 +71,9 @@ extern const char *bin_name;
 extern json_writer_t *json_wtr;
 extern bool json_output;
 
+void p_err(const char *fmt, ...);
+void p_info(const char *fmt, ...);
+
 bool is_prefix(const char *pfx, const char *str);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __attribute__((noreturn));
@@ -97,35 +100,4 @@ int prog_parse_fd(int *argc, char ***argv);
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
 void print_hex_data_json(uint8_t *data, size_t len);
 
-static inline void p_err(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	if (json_output) {
-		jsonw_start_object(json_wtr);
-		jsonw_name(json_wtr, "error");
-		jsonw_vprintf_enquote(json_wtr, fmt, ap);
-		jsonw_end_object(json_wtr);
-	} else {
-		fprintf(stderr, "Error: ");
-		vfprintf(stderr, fmt, ap);
-		fprintf(stderr, "\n");
-	}
-	va_end(ap);
-}
-
-static inline void p_info(const char *fmt, ...)
-{
-	va_list ap;
-
-	if (json_output)
-		return;
-
-	va_start(ap, fmt);
-	vfprintf(stderr, fmt, ap);
-	fprintf(stderr, "\n");
-	va_end(ap);
-}
-
 #endif
-- 
cgit v1.2.3


From ebc614f687369f9df99828572b1d85a7c2de3d92 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sun, 5 Nov 2017 08:15:32 -0500
Subject: bpf, cgroup: implement eBPF-based device controller for cgroup v2

Cgroup v2 lacks the device controller, provided by cgroup v1.
This patch adds a new eBPF program type, which in combination
of previously added ability to attach multiple eBPF programs
to a cgroup, will provide a similar functionality, but with some
additional flexibility.

This patch introduces a BPF_PROG_TYPE_CGROUP_DEVICE program type.
A program takes major and minor device numbers, device type
(block/character) and access type (mknod/read/write) as parameters
and returns an integer which defines if the operation should be
allowed or terminated with -EPERM.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf-cgroup.h     | 15 ++++++++++
 include/linux/bpf_types.h      |  3 ++
 include/linux/device_cgroup.h  |  8 ++++-
 include/uapi/linux/bpf.h       | 15 ++++++++++
 kernel/bpf/cgroup.c            | 67 ++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           |  7 +++++
 kernel/bpf/verifier.c          |  1 +
 tools/include/uapi/linux/bpf.h | 15 ++++++++++
 8 files changed, 130 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 87a7db9feb38..a7f16e0f8d68 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -67,6 +67,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 				     struct bpf_sock_ops_kern *sock_ops,
 				     enum bpf_attach_type type);
 
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+				      short access, enum bpf_attach_type type);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -112,6 +115,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 	}								       \
 	__ret;								       \
 })
+
+#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access)	      \
+({									      \
+	int __ret = 0;							      \
+	if (cgroup_bpf_enabled)						      \
+		__ret = __cgroup_bpf_check_dev_permission(type, major, minor, \
+							  access,	      \
+							  BPF_CGROUP_DEVICE); \
+									      \
+	__ret;								      \
+})
 #else
 
 struct cgroup_bpf {};
@@ -122,6 +136,7 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 53c5b9ad7220..978c1d9c9383 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -19,6 +19,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
 BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
 #endif
+#ifdef CONFIG_CGROUP_BPF
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
+#endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index 2d93d7ecd479..8557efe096dc 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/fs.h>
+#include <linux/bpf-cgroup.h>
 
 #define DEVCG_ACC_MKNOD 1
 #define DEVCG_ACC_READ  2
@@ -19,10 +20,15 @@ static inline int __devcgroup_check_permission(short type, u32 major, u32 minor,
 { return 0; }
 #endif
 
-#ifdef CONFIG_CGROUP_DEVICE
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
 					     short access)
 {
+	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
+
+	if (rc)
+		return -EPERM;
+
 	return __devcgroup_check_permission(type, major, minor, access);
 }
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4455dd195201..e880ae6434ee 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -132,6 +132,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_XMIT,
 	BPF_PROG_TYPE_SOCK_OPS,
 	BPF_PROG_TYPE_SK_SKB,
+	BPF_PROG_TYPE_CGROUP_DEVICE,
 };
 
 enum bpf_attach_type {
@@ -141,6 +142,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_SOCK_OPS,
 	BPF_SK_SKB_STREAM_PARSER,
 	BPF_SK_SKB_STREAM_VERDICT,
+	BPF_CGROUP_DEVICE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -991,4 +993,17 @@ struct bpf_perf_event_value {
 	__u64 running;
 };
 
+#define BPF_DEVCG_ACC_MKNOD	(1ULL << 0)
+#define BPF_DEVCG_ACC_READ	(1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE	(1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK	(1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR	(1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+	__u32 access_type; /* (access << 16) | type */
+	__u32 major;
+	__u32 minor;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 3db5a17fcfe8..b789ab78d28f 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -522,3 +522,70 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
+
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+				      short access, enum bpf_attach_type type)
+{
+	struct cgroup *cgrp;
+	struct bpf_cgroup_dev_ctx ctx = {
+		.access_type = (access << 16) | dev_type,
+		.major = major,
+		.minor = minor,
+	};
+	int allow = 1;
+
+	rcu_read_lock();
+	cgrp = task_dfl_cgroup(current);
+	allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx,
+				   BPF_PROG_RUN);
+	rcu_read_unlock();
+
+	return !allow;
+}
+EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
+
+static const struct bpf_func_proto *
+cgroup_dev_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_trace_printk:
+		if (capable(CAP_SYS_ADMIN))
+			return bpf_get_trace_printk_proto();
+	default:
+		return NULL;
+	}
+}
+
+static bool cgroup_dev_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       struct bpf_insn_access_aux *info)
+{
+	if (type == BPF_WRITE)
+		return false;
+
+	if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx))
+		return false;
+	/* The verifier guarantees that size > 0. */
+	if (off % size != 0)
+		return false;
+	if (size != sizeof(__u32))
+		return false;
+
+	return true;
+}
+
+const struct bpf_prog_ops cg_dev_prog_ops = {
+};
+
+const struct bpf_verifier_ops cg_dev_verifier_ops = {
+	.get_func_proto		= cgroup_dev_func_proto,
+	.is_valid_access	= cgroup_dev_is_valid_access,
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 416d70cdfc76..09badc37e864 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1326,6 +1326,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_SOCK_OPS:
 		ptype = BPF_PROG_TYPE_SOCK_OPS;
 		break;
+	case BPF_CGROUP_DEVICE:
+		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
 		return sockmap_get_from_fd(attr, true);
@@ -1378,6 +1381,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_CGROUP_SOCK_OPS:
 		ptype = BPF_PROG_TYPE_SOCK_OPS;
 		break;
+	case BPF_CGROUP_DEVICE:
+		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
 		return sockmap_get_from_fd(attr, false);
@@ -1420,6 +1426,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET_EGRESS:
 	case BPF_CGROUP_INET_SOCK_CREATE:
 	case BPF_CGROUP_SOCK_OPS:
+	case BPF_CGROUP_DEVICE:
 		break;
 	default:
 		return -EINVAL;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index add845fe788a..4a942e2e753d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3124,6 +3124,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
 		break;
 	default:
 		return 0;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e92f62cf933a..b280f37cd057 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -131,6 +131,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_XMIT,
 	BPF_PROG_TYPE_SOCK_OPS,
 	BPF_PROG_TYPE_SK_SKB,
+	BPF_PROG_TYPE_CGROUP_DEVICE,
 };
 
 enum bpf_attach_type {
@@ -140,6 +141,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_SOCK_OPS,
 	BPF_SK_SKB_STREAM_PARSER,
 	BPF_SK_SKB_STREAM_VERDICT,
+	BPF_CGROUP_DEVICE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -990,4 +992,17 @@ struct bpf_perf_event_value {
 	__u64 running;
 };
 
+#define BPF_DEVCG_ACC_MKNOD	(1ULL << 0)
+#define BPF_DEVCG_ACC_READ	(1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE	(1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK	(1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR	(1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+	__u32 access_type; /* (access << 16) | type */
+	__u32 major;
+	__u32 minor;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From 9d1f15941967cd80fc3baa3322751fab532f98a4 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sun, 5 Nov 2017 08:15:33 -0500
Subject: bpf: move cgroup_helpers from samples/bpf/ to
 tools/testing/selftesting/bpf/

The purpose of this move is to use these files in bpf tests.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/Makefile                         |   5 +-
 samples/bpf/cgroup_helpers.c                 | 178 ---------------------------
 samples/bpf/cgroup_helpers.h                 |  17 ---
 tools/testing/selftests/bpf/Makefile         |   2 +-
 tools/testing/selftests/bpf/cgroup_helpers.c | 178 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/cgroup_helpers.h |  17 +++
 6 files changed, 199 insertions(+), 198 deletions(-)
 delete mode 100644 samples/bpf/cgroup_helpers.c
 delete mode 100644 samples/bpf/cgroup_helpers.h
 create mode 100644 tools/testing/selftests/bpf/cgroup_helpers.c
 create mode 100644 tools/testing/selftests/bpf/cgroup_helpers.h

(limited to 'tools')

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 6a9321ec348a..5994075b080d 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -46,6 +46,7 @@ hostprogs-y += syscall_tp
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
+CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 
 test_lru_dist-objs := test_lru_dist.o $(LIBBPF)
 sock_example-objs := sock_example.o $(LIBBPF)
@@ -69,13 +70,13 @@ map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o
 test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o
 test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o
 test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o
-test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o cgroup_helpers.o
+test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o $(CGROUP_HELPERS)
 test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o
 test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o
 xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o
 # reuse xdp1 source intentionally
 xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o
-test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) cgroup_helpers.o \
+test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) $(CGROUP_HELPERS) \
 				       test_current_task_under_cgroup_user.o
 trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o
 sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
diff --git a/samples/bpf/cgroup_helpers.c b/samples/bpf/cgroup_helpers.c
deleted file mode 100644
index f3bca3ade0f3..000000000000
--- a/samples/bpf/cgroup_helpers.c
+++ /dev/null
@@ -1,178 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-#include <sched.h>
-#include <sys/mount.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-#include <linux/limits.h>
-#include <stdio.h>
-#include <linux/sched.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <ftw.h>
-
-
-#include "cgroup_helpers.h"
-
-/*
- * To avoid relying on the system setup, when setup_cgroup_env is called
- * we create a new mount namespace, and cgroup namespace. The cgroup2
- * root is mounted at CGROUP_MOUNT_PATH
- *
- * Unfortunately, most people don't have cgroupv2 enabled at this point in time.
- * It's easier to create our own mount namespace and manage it ourselves.
- *
- * We assume /mnt exists.
- */
-
-#define WALK_FD_LIMIT			16
-#define CGROUP_MOUNT_PATH		"/mnt"
-#define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
-#define format_cgroup_path(buf, path) \
-	snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
-		 CGROUP_WORK_DIR, path)
-
-/**
- * setup_cgroup_environment() - Setup the cgroup environment
- *
- * After calling this function, cleanup_cgroup_environment should be called
- * once testing is complete.
- *
- * This function will print an error to stderr and return 1 if it is unable
- * to setup the cgroup environment. If setup is successful, 0 is returned.
- */
-int setup_cgroup_environment(void)
-{
-	char cgroup_workdir[PATH_MAX + 1];
-
-	format_cgroup_path(cgroup_workdir, "");
-
-	if (unshare(CLONE_NEWNS)) {
-		log_err("unshare");
-		return 1;
-	}
-
-	if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
-		log_err("mount fakeroot");
-		return 1;
-	}
-
-	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
-		log_err("mount cgroup2");
-		return 1;
-	}
-
-	/* Cleanup existing failed runs, now that the environment is setup */
-	cleanup_cgroup_environment();
-
-	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
-		log_err("mkdir cgroup work dir");
-		return 1;
-	}
-
-	return 0;
-}
-
-static int nftwfunc(const char *filename, const struct stat *statptr,
-		    int fileflags, struct FTW *pfwt)
-{
-	if ((fileflags & FTW_D) && rmdir(filename))
-		log_err("Removing cgroup: %s", filename);
-	return 0;
-}
-
-
-static int join_cgroup_from_top(char *cgroup_path)
-{
-	char cgroup_procs_path[PATH_MAX + 1];
-	pid_t pid = getpid();
-	int fd, rc = 0;
-
-	snprintf(cgroup_procs_path, sizeof(cgroup_procs_path),
-		 "%s/cgroup.procs", cgroup_path);
-
-	fd = open(cgroup_procs_path, O_WRONLY);
-	if (fd < 0) {
-		log_err("Opening Cgroup Procs: %s", cgroup_procs_path);
-		return 1;
-	}
-
-	if (dprintf(fd, "%d\n", pid) < 0) {
-		log_err("Joining Cgroup");
-		rc = 1;
-	}
-
-	close(fd);
-	return rc;
-}
-
-/**
- * join_cgroup() - Join a cgroup
- * @path: The cgroup path, relative to the workdir, to join
- *
- * This function expects a cgroup to already be created, relative to the cgroup
- * work dir, and it joins it. For example, passing "/my-cgroup" as the path
- * would actually put the calling process into the cgroup
- * "/cgroup-test-work-dir/my-cgroup"
- *
- * On success, it returns 0, otherwise on failure it returns 1.
- */
-int join_cgroup(char *path)
-{
-	char cgroup_path[PATH_MAX + 1];
-
-	format_cgroup_path(cgroup_path, path);
-	return join_cgroup_from_top(cgroup_path);
-}
-
-/**
- * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
- *
- * This is an idempotent function to delete all temporary cgroups that
- * have been created during the test, including the cgroup testing work
- * directory.
- *
- * At call time, it moves the calling process to the root cgroup, and then
- * runs the deletion process. It is idempotent, and should not fail, unless
- * a process is lingering.
- *
- * On failure, it will print an error to stderr, and try to continue.
- */
-void cleanup_cgroup_environment(void)
-{
-	char cgroup_workdir[PATH_MAX + 1];
-
-	format_cgroup_path(cgroup_workdir, "");
-	join_cgroup_from_top(CGROUP_MOUNT_PATH);
-	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
-}
-
-/**
- * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
- * @path: The cgroup path, relative to the workdir, to join
- *
- * This function creates a cgroup under the top level workdir and returns the
- * file descriptor. It is idempotent.
- *
- * On success, it returns the file descriptor. On failure it returns 0.
- * If there is a failure, it prints the error to stderr.
- */
-int create_and_get_cgroup(char *path)
-{
-	char cgroup_path[PATH_MAX + 1];
-	int fd;
-
-	format_cgroup_path(cgroup_path, path);
-	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
-		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
-		return 0;
-	}
-
-	fd = open(cgroup_path, O_RDONLY);
-	if (fd < 0) {
-		log_err("Opening Cgroup");
-		return 0;
-	}
-
-	return fd;
-}
diff --git a/samples/bpf/cgroup_helpers.h b/samples/bpf/cgroup_helpers.h
deleted file mode 100644
index 06485e0002b3..000000000000
--- a/samples/bpf/cgroup_helpers.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __CGROUP_HELPERS_H
-#define __CGROUP_HELPERS_H
-#include <errno.h>
-#include <string.h>
-
-#define clean_errno() (errno == 0 ? "None" : strerror(errno))
-#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
-	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
-
-
-int create_and_get_cgroup(char *path);
-int join_cgroup(char *path);
-int setup_cgroup_environment(void);
-void cleanup_cgroup_environment(void);
-
-#endif
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4f0734aa6e93..9fbb02638198 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
 
 include ../lib.mk
 
-BPFOBJ := $(OUTPUT)/libbpf.a
+BPFOBJ := $(OUTPUT)/libbpf.a $(OUTPUT)/cgroup_helpers.c
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
 
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
new file mode 100644
index 000000000000..f3bca3ade0f3
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <linux/limits.h>
+#include <stdio.h>
+#include <linux/sched.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <ftw.h>
+
+
+#include "cgroup_helpers.h"
+
+/*
+ * To avoid relying on the system setup, when setup_cgroup_env is called
+ * we create a new mount namespace, and cgroup namespace. The cgroup2
+ * root is mounted at CGROUP_MOUNT_PATH
+ *
+ * Unfortunately, most people don't have cgroupv2 enabled at this point in time.
+ * It's easier to create our own mount namespace and manage it ourselves.
+ *
+ * We assume /mnt exists.
+ */
+
+#define WALK_FD_LIMIT			16
+#define CGROUP_MOUNT_PATH		"/mnt"
+#define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
+#define format_cgroup_path(buf, path) \
+	snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
+		 CGROUP_WORK_DIR, path)
+
+/**
+ * setup_cgroup_environment() - Setup the cgroup environment
+ *
+ * After calling this function, cleanup_cgroup_environment should be called
+ * once testing is complete.
+ *
+ * This function will print an error to stderr and return 1 if it is unable
+ * to setup the cgroup environment. If setup is successful, 0 is returned.
+ */
+int setup_cgroup_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, "");
+
+	if (unshare(CLONE_NEWNS)) {
+		log_err("unshare");
+		return 1;
+	}
+
+	if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
+		log_err("mount fakeroot");
+		return 1;
+	}
+
+	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
+		log_err("mount cgroup2");
+		return 1;
+	}
+
+	/* Cleanup existing failed runs, now that the environment is setup */
+	cleanup_cgroup_environment();
+
+	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
+		log_err("mkdir cgroup work dir");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int nftwfunc(const char *filename, const struct stat *statptr,
+		    int fileflags, struct FTW *pfwt)
+{
+	if ((fileflags & FTW_D) && rmdir(filename))
+		log_err("Removing cgroup: %s", filename);
+	return 0;
+}
+
+
+static int join_cgroup_from_top(char *cgroup_path)
+{
+	char cgroup_procs_path[PATH_MAX + 1];
+	pid_t pid = getpid();
+	int fd, rc = 0;
+
+	snprintf(cgroup_procs_path, sizeof(cgroup_procs_path),
+		 "%s/cgroup.procs", cgroup_path);
+
+	fd = open(cgroup_procs_path, O_WRONLY);
+	if (fd < 0) {
+		log_err("Opening Cgroup Procs: %s", cgroup_procs_path);
+		return 1;
+	}
+
+	if (dprintf(fd, "%d\n", pid) < 0) {
+		log_err("Joining Cgroup");
+		rc = 1;
+	}
+
+	close(fd);
+	return rc;
+}
+
+/**
+ * join_cgroup() - Join a cgroup
+ * @path: The cgroup path, relative to the workdir, to join
+ *
+ * This function expects a cgroup to already be created, relative to the cgroup
+ * work dir, and it joins it. For example, passing "/my-cgroup" as the path
+ * would actually put the calling process into the cgroup
+ * "/cgroup-test-work-dir/my-cgroup"
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_cgroup(char *path)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_path, path);
+	return join_cgroup_from_top(cgroup_path);
+}
+
+/**
+ * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
+ *
+ * This is an idempotent function to delete all temporary cgroups that
+ * have been created during the test, including the cgroup testing work
+ * directory.
+ *
+ * At call time, it moves the calling process to the root cgroup, and then
+ * runs the deletion process. It is idempotent, and should not fail, unless
+ * a process is lingering.
+ *
+ * On failure, it will print an error to stderr, and try to continue.
+ */
+void cleanup_cgroup_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, "");
+	join_cgroup_from_top(CGROUP_MOUNT_PATH);
+	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
+
+/**
+ * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
+ * @path: The cgroup path, relative to the workdir, to join
+ *
+ * This function creates a cgroup under the top level workdir and returns the
+ * file descriptor. It is idempotent.
+ *
+ * On success, it returns the file descriptor. On failure it returns 0.
+ * If there is a failure, it prints the error to stderr.
+ */
+int create_and_get_cgroup(char *path)
+{
+	char cgroup_path[PATH_MAX + 1];
+	int fd;
+
+	format_cgroup_path(cgroup_path, path);
+	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
+		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
+		return 0;
+	}
+
+	fd = open(cgroup_path, O_RDONLY);
+	if (fd < 0) {
+		log_err("Opening Cgroup");
+		return 0;
+	}
+
+	return fd;
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
new file mode 100644
index 000000000000..06485e0002b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __CGROUP_HELPERS_H
+#define __CGROUP_HELPERS_H
+#include <errno.h>
+#include <string.h>
+
+#define clean_errno() (errno == 0 ? "None" : strerror(errno))
+#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
+
+
+int create_and_get_cgroup(char *path);
+int join_cgroup(char *path);
+int setup_cgroup_environment(void);
+void cleanup_cgroup_environment(void);
+
+#endif
-- 
cgit v1.2.3


From 37f1ba0909dfa12c75f8e8ea7a2f01355ebd60f1 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sun, 5 Nov 2017 08:15:34 -0500
Subject: selftests/bpf: add a test for device cgroup controller

Add a test for device cgroup controller.

The test loads a simple bpf program which logs all
device access attempts using trace_printk() and forbids
all operations except operations with /dev/zero and
/dev/urandom.

Then the test creates and joins a test cgroup, and attaches
the bpf program to it.

Then it tries to perform some simple device operations
and checks the result:

  create /dev/null (should fail)
  create /dev/zero (should pass)
  copy data from /dev/urandom to /dev/zero (should pass)
  copy data from /dev/urandom to /dev/full (should fail)
  copy data from /dev/random to /dev/zero (should fail)

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/Makefile          |  4 +-
 tools/testing/selftests/bpf/dev_cgroup.c      | 60 +++++++++++++++++
 tools/testing/selftests/bpf/test_dev_cgroup.c | 93 +++++++++++++++++++++++++++
 3 files changed, 155 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/dev_cgroup.c
 create mode 100644 tools/testing/selftests/bpf/test_dev_cgroup.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 9fbb02638198..333a48655ee0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -13,11 +13,11 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i
 LDLIBS += -lcap -lelf
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align test_verifier_log
+	test_align test_verifier_log test_dev_cgroup
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
-	sockmap_verdict_prog.o
+	sockmap_verdict_prog.o dev_cgroup.o
 
 TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
 
diff --git a/tools/testing/selftests/bpf/dev_cgroup.c b/tools/testing/selftests/bpf/dev_cgroup.c
new file mode 100644
index 000000000000..ce41a3475f27
--- /dev/null
+++ b/tools/testing/selftests/bpf/dev_cgroup.c
@@ -0,0 +1,60 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+SEC("cgroup/dev")
+int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
+{
+	short type = ctx->access_type & 0xFFFF;
+#ifdef DEBUG
+	short access = ctx->access_type >> 16;
+	char fmt[] = "  %d:%d    \n";
+
+	switch (type) {
+	case BPF_DEVCG_DEV_BLOCK:
+		fmt[0] = 'b';
+		break;
+	case BPF_DEVCG_DEV_CHAR:
+		fmt[0] = 'c';
+		break;
+	default:
+		fmt[0] = '?';
+		break;
+	}
+
+	if (access & BPF_DEVCG_ACC_READ)
+		fmt[8] = 'r';
+
+	if (access & BPF_DEVCG_ACC_WRITE)
+		fmt[9] = 'w';
+
+	if (access & BPF_DEVCG_ACC_MKNOD)
+		fmt[10] = 'm';
+
+	bpf_trace_printk(fmt, sizeof(fmt), ctx->major, ctx->minor);
+#endif
+
+	/* Allow access to /dev/zero and /dev/random.
+	 * Forbid everything else.
+	 */
+	if (ctx->major != 1 || type != BPF_DEVCG_DEV_CHAR)
+		return 0;
+
+	switch (ctx->minor) {
+	case 5: /* 1:5 /dev/zero */
+	case 9: /* 1:9 /dev/urandom */
+		return 1;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
new file mode 100644
index 000000000000..02c85d6c89b0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_dev_cgroup.c
@@ -0,0 +1,93 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+
+#define DEV_CGROUP_PROG "./dev_cgroup.o"
+
+#define TEST_CGROUP "test-bpf-based-device-cgroup/"
+
+int main(int argc, char **argv)
+{
+	struct bpf_object *obj;
+	int error = EXIT_FAILURE;
+	int prog_fd, cgroup_fd;
+	__u32 prog_cnt;
+
+	if (bpf_prog_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE,
+			  &obj, &prog_fd)) {
+		printf("Failed to load DEV_CGROUP program\n");
+		goto err;
+	}
+
+	if (setup_cgroup_environment()) {
+		printf("Failed to load DEV_CGROUP program\n");
+		goto err;
+	}
+
+	/* Create a cgroup, get fd, and join it */
+	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	if (!cgroup_fd) {
+		printf("Failed to create test cgroup\n");
+		goto err;
+	}
+
+	if (join_cgroup(TEST_CGROUP)) {
+		printf("Failed to join cgroup\n");
+		goto err;
+	}
+
+	/* Attach bpf program */
+	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_DEVICE, 0)) {
+		printf("Failed to attach DEV_CGROUP program");
+		goto err;
+	}
+
+	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_DEVICE, 0, NULL, NULL,
+			   &prog_cnt)) {
+		printf("Failed to query attached programs");
+		goto err;
+	}
+
+	/* All operations with /dev/zero and and /dev/urandom are allowed,
+	 * everything else is forbidden.
+	 */
+	assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
+	assert(system("mknod /tmp/test_dev_cgroup_null c 1 3"));
+	assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
+
+	/* /dev/zero is whitelisted */
+	assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
+	assert(system("mknod /tmp/test_dev_cgroup_zero c 1 5") == 0);
+	assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
+
+	assert(system("dd if=/dev/urandom of=/dev/zero count=64") == 0);
+
+	/* src is allowed, target is forbidden */
+	assert(system("dd if=/dev/urandom of=/dev/full count=64"));
+
+	/* src is forbidden, target is allowed */
+	assert(system("dd if=/dev/random of=/dev/zero count=64"));
+
+	error = 0;
+	printf("test_dev_cgroup:PASS\n");
+
+err:
+	cleanup_cgroup_environment();
+
+	return error;
+}
-- 
cgit v1.2.3


From 6a77cff819ae3e31992bde6432c9b5720748a89b Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Mon, 6 Nov 2017 07:21:50 -0600
Subject: objtool: Move synced files to their original relative locations

This will enable more straightforward comparisons, and it also makes the
files 100% identical.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/407b2aaa317741f48fcf821592c0e96ab3be1890.1509974346.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/objtool/.gitignore                           |    2 +-
 tools/objtool/Makefile                             |   22 +-
 tools/objtool/arch/x86/Build                       |   10 +-
 tools/objtool/arch/x86/decode.c                    |    6 +-
 tools/objtool/arch/x86/include/asm/inat.h          |  234 +++++
 tools/objtool/arch/x86/include/asm/inat_types.h    |   29 +
 tools/objtool/arch/x86/include/asm/insn.h          |  211 ++++
 tools/objtool/arch/x86/include/asm/orc_types.h     |  107 ++
 tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk  |  393 --------
 tools/objtool/arch/x86/insn/inat.c                 |   97 --
 tools/objtool/arch/x86/insn/inat.h                 |  234 -----
 tools/objtool/arch/x86/insn/inat_types.h           |   29 -
 tools/objtool/arch/x86/insn/insn.c                 |  606 -----------
 tools/objtool/arch/x86/insn/insn.h                 |  211 ----
 tools/objtool/arch/x86/insn/x86-opcode-map.txt     | 1063 --------------------
 tools/objtool/arch/x86/lib/inat.c                  |   97 ++
 tools/objtool/arch/x86/lib/insn.c                  |  606 +++++++++++
 tools/objtool/arch/x86/lib/x86-opcode-map.txt      | 1063 ++++++++++++++++++++
 tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk |  393 ++++++++
 tools/objtool/orc.h                                |    2 +-
 tools/objtool/orc_types.h                          |  107 --
 21 files changed, 2762 insertions(+), 2760 deletions(-)
 create mode 100644 tools/objtool/arch/x86/include/asm/inat.h
 create mode 100644 tools/objtool/arch/x86/include/asm/inat_types.h
 create mode 100644 tools/objtool/arch/x86/include/asm/insn.h
 create mode 100644 tools/objtool/arch/x86/include/asm/orc_types.h
 delete mode 100644 tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
 delete mode 100644 tools/objtool/arch/x86/insn/inat.c
 delete mode 100644 tools/objtool/arch/x86/insn/inat.h
 delete mode 100644 tools/objtool/arch/x86/insn/inat_types.h
 delete mode 100644 tools/objtool/arch/x86/insn/insn.c
 delete mode 100644 tools/objtool/arch/x86/insn/insn.h
 delete mode 100644 tools/objtool/arch/x86/insn/x86-opcode-map.txt
 create mode 100644 tools/objtool/arch/x86/lib/inat.c
 create mode 100644 tools/objtool/arch/x86/lib/insn.c
 create mode 100644 tools/objtool/arch/x86/lib/x86-opcode-map.txt
 create mode 100644 tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
 delete mode 100644 tools/objtool/orc_types.h

(limited to 'tools')

diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore
index d3102c865a95..914cff12899b 100644
--- a/tools/objtool/.gitignore
+++ b/tools/objtool/.gitignore
@@ -1,3 +1,3 @@
-arch/x86/insn/inat-tables.c
+arch/x86/lib/inat-tables.c
 objtool
 fixdep
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 424b1965d06f..c6a19d946ec1 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -25,7 +25,9 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi
+INCLUDES := -I$(srctree)/tools/include \
+	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
+	    -I$(srctree)/tools/objtool/arch/$(HOSTARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
 CFLAGS   += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
@@ -46,16 +48,16 @@ $(OBJTOOL_IN): fixdep FORCE
 $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
 	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
 	test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
-	diff -I'^#include' arch/x86/insn/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
-	diff -I'^#include' arch/x86/insn/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
-	diff arch/x86/insn/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
-	diff arch/x86/insn/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
-	diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
-	diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
-	diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
+	diff arch/x86/lib/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
+	diff arch/x86/lib/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
+	diff arch/x86/lib/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
+	diff arch/x86/tools/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
+	diff arch/x86/include/asm/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
+	diff arch/x86/include/asm/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
+	diff arch/x86/include/asm/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
 	|| echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
 	@(test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
-	diff ../../arch/x86/include/asm/orc_types.h orc_types.h >/dev/null) \
+	diff ../../arch/x86/include/asm/orc_types.h arch/x86/include/asm/orc_types.h >/dev/null) \
 	|| echo "warning: objtool: orc_types.h differs from kernel" >&2 )) || true
 	$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
@@ -66,7 +68,7 @@ $(LIBSUBCMD): fixdep FORCE
 clean:
 	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
 	$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-	$(Q)$(RM) $(OUTPUT)arch/x86/insn/inat-tables.c $(OUTPUT)fixdep
+	$(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep
 
 FORCE:
 
diff --git a/tools/objtool/arch/x86/Build b/tools/objtool/arch/x86/Build
index debbdb0b5c43..b998412c017d 100644
--- a/tools/objtool/arch/x86/Build
+++ b/tools/objtool/arch/x86/Build
@@ -1,12 +1,12 @@
 objtool-y += decode.o
 
-inat_tables_script = arch/x86/insn/gen-insn-attr-x86.awk
-inat_tables_maps = arch/x86/insn/x86-opcode-map.txt
+inat_tables_script = arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = arch/x86/lib/x86-opcode-map.txt
 
-$(OUTPUT)arch/x86/insn/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+$(OUTPUT)arch/x86/lib/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@
 
-$(OUTPUT)arch/x86/decode.o: $(OUTPUT)arch/x86/insn/inat-tables.c
+$(OUTPUT)arch/x86/decode.o: $(OUTPUT)arch/x86/lib/inat-tables.c
 
-CFLAGS_decode.o += -I$(OUTPUT)arch/x86/insn
+CFLAGS_decode.o += -I$(OUTPUT)arch/x86/lib
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 34a579f806e3..8acfc47af70e 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -19,9 +19,9 @@
 #include <stdlib.h>
 
 #define unlikely(cond) (cond)
-#include "insn/insn.h"
-#include "insn/inat.c"
-#include "insn/insn.c"
+#include <asm/insn.h>
+#include "lib/inat.c"
+#include "lib/insn.c"
 
 #include "../../elf.h"
 #include "../../arch.h"
diff --git a/tools/objtool/arch/x86/include/asm/inat.h b/tools/objtool/arch/x86/include/asm/inat.h
new file mode 100644
index 000000000000..02aff0867211
--- /dev/null
+++ b/tools/objtool/arch/x86/include/asm/inat.h
@@ -0,0 +1,234 @@
+#ifndef _ASM_X86_INAT_H
+#define _ASM_X86_INAT_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <asm/inat_types.h>
+
+/*
+ * Internal bits. Don't use bitmasks directly, because these bits are
+ * unstable. You should use checking functions.
+ */
+
+#define INAT_OPCODE_TABLE_SIZE 256
+#define INAT_GROUP_TABLE_SIZE 8
+
+/* Legacy last prefixes */
+#define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
+#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
+#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
+/* Other Legacy prefixes */
+#define INAT_PFX_LOCK	4	/* 0xF0 */
+#define INAT_PFX_CS	5	/* 0x2E */
+#define INAT_PFX_DS	6	/* 0x3E */
+#define INAT_PFX_ES	7	/* 0x26 */
+#define INAT_PFX_FS	8	/* 0x64 */
+#define INAT_PFX_GS	9	/* 0x65 */
+#define INAT_PFX_SS	10	/* 0x36 */
+#define INAT_PFX_ADDRSZ	11	/* 0x67 */
+/* x86-64 REX prefix */
+#define INAT_PFX_REX	12	/* 0x4X */
+/* AVX VEX prefixes */
+#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
+#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
+
+#define INAT_LSTPFX_MAX	3
+#define INAT_LGCPFX_MAX	11
+
+/* Immediate size */
+#define INAT_IMM_BYTE		1
+#define INAT_IMM_WORD		2
+#define INAT_IMM_DWORD		3
+#define INAT_IMM_QWORD		4
+#define INAT_IMM_PTR		5
+#define INAT_IMM_VWORD32	6
+#define INAT_IMM_VWORD		7
+
+/* Legacy prefix */
+#define INAT_PFX_OFFS	0
+#define INAT_PFX_BITS	4
+#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
+#define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
+/* Escape opcodes */
+#define INAT_ESC_OFFS	(INAT_PFX_OFFS + INAT_PFX_BITS)
+#define INAT_ESC_BITS	2
+#define INAT_ESC_MAX	((1 << INAT_ESC_BITS) - 1)
+#define INAT_ESC_MASK	(INAT_ESC_MAX << INAT_ESC_OFFS)
+/* Group opcodes (1-16) */
+#define INAT_GRP_OFFS	(INAT_ESC_OFFS + INAT_ESC_BITS)
+#define INAT_GRP_BITS	5
+#define INAT_GRP_MAX	((1 << INAT_GRP_BITS) - 1)
+#define INAT_GRP_MASK	(INAT_GRP_MAX << INAT_GRP_OFFS)
+/* Immediates */
+#define INAT_IMM_OFFS	(INAT_GRP_OFFS + INAT_GRP_BITS)
+#define INAT_IMM_BITS	3
+#define INAT_IMM_MASK	(((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
+/* Flags */
+#define INAT_FLAG_OFFS	(INAT_IMM_OFFS + INAT_IMM_BITS)
+#define INAT_MODRM	(1 << (INAT_FLAG_OFFS))
+#define INAT_FORCE64	(1 << (INAT_FLAG_OFFS + 1))
+#define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
+#define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
+#define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
+#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
+#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
+/* Attribute making macros for attribute tables */
+#define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
+#define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
+#define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
+#define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
+
+/* Attribute search APIs */
+extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
+extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
+					     int lpfx_id,
+					     insn_attr_t esc_attr);
+extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
+					    int lpfx_id,
+					    insn_attr_t esc_attr);
+extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
+					  insn_byte_t vex_m,
+					  insn_byte_t vex_pp);
+
+/* Attribute checking functions */
+static inline int inat_is_legacy_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr && attr <= INAT_LGCPFX_MAX;
+}
+
+static inline int inat_is_address_size_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
+}
+
+static inline int inat_is_operand_size_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
+}
+
+static inline int inat_is_rex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
+}
+
+static inline int inat_last_prefix_id(insn_attr_t attr)
+{
+	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
+		return 0;
+	else
+		return attr & INAT_PFX_MASK;
+}
+
+static inline int inat_is_vex_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_vex3_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_escape(insn_attr_t attr)
+{
+	return attr & INAT_ESC_MASK;
+}
+
+static inline int inat_escape_id(insn_attr_t attr)
+{
+	return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
+}
+
+static inline int inat_is_group(insn_attr_t attr)
+{
+	return attr & INAT_GRP_MASK;
+}
+
+static inline int inat_group_id(insn_attr_t attr)
+{
+	return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
+}
+
+static inline int inat_group_common_attribute(insn_attr_t attr)
+{
+	return attr & ~INAT_GRP_MASK;
+}
+
+static inline int inat_has_immediate(insn_attr_t attr)
+{
+	return attr & INAT_IMM_MASK;
+}
+
+static inline int inat_immediate_size(insn_attr_t attr)
+{
+	return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
+}
+
+static inline int inat_has_modrm(insn_attr_t attr)
+{
+	return attr & INAT_MODRM;
+}
+
+static inline int inat_is_force64(insn_attr_t attr)
+{
+	return attr & INAT_FORCE64;
+}
+
+static inline int inat_has_second_immediate(insn_attr_t attr)
+{
+	return attr & INAT_SCNDIMM;
+}
+
+static inline int inat_has_moffset(insn_attr_t attr)
+{
+	return attr & INAT_MOFFSET;
+}
+
+static inline int inat_has_variant(insn_attr_t attr)
+{
+	return attr & INAT_VARIANT;
+}
+
+static inline int inat_accept_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXOK;
+}
+
+static inline int inat_must_vex(insn_attr_t attr)
+{
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
+}
+#endif
diff --git a/tools/objtool/arch/x86/include/asm/inat_types.h b/tools/objtool/arch/x86/include/asm/inat_types.h
new file mode 100644
index 000000000000..cb3c20ce39cf
--- /dev/null
+++ b/tools/objtool/arch/x86/include/asm/inat_types.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_INAT_TYPES_H
+#define _ASM_X86_INAT_TYPES_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+/* Instruction attributes */
+typedef unsigned int insn_attr_t;
+typedef unsigned char insn_byte_t;
+typedef signed int insn_value_t;
+
+#endif
diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h
new file mode 100644
index 000000000000..b3e32b010ab1
--- /dev/null
+++ b/tools/objtool/arch/x86/include/asm/insn.h
@@ -0,0 +1,211 @@
+#ifndef _ASM_X86_INSN_H
+#define _ASM_X86_INSN_H
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+/* insn_attr_t is defined in inat.h */
+#include <asm/inat.h>
+
+struct insn_field {
+	union {
+		insn_value_t value;
+		insn_byte_t bytes[4];
+	};
+	/* !0 if we've run insn_get_xxx() for this field */
+	unsigned char got;
+	unsigned char nbytes;
+};
+
+struct insn {
+	struct insn_field prefixes;	/*
+					 * Prefixes
+					 * prefixes.bytes[3]: last prefix
+					 */
+	struct insn_field rex_prefix;	/* REX prefix */
+	struct insn_field vex_prefix;	/* VEX prefix */
+	struct insn_field opcode;	/*
+					 * opcode.bytes[0]: opcode1
+					 * opcode.bytes[1]: opcode2
+					 * opcode.bytes[2]: opcode3
+					 */
+	struct insn_field modrm;
+	struct insn_field sib;
+	struct insn_field displacement;
+	union {
+		struct insn_field immediate;
+		struct insn_field moffset1;	/* for 64bit MOV */
+		struct insn_field immediate1;	/* for 64bit imm or off16/32 */
+	};
+	union {
+		struct insn_field moffset2;	/* for 64bit MOV */
+		struct insn_field immediate2;	/* for 64bit imm or seg16 */
+	};
+
+	insn_attr_t attr;
+	unsigned char opnd_bytes;
+	unsigned char addr_bytes;
+	unsigned char length;
+	unsigned char x86_64;
+
+	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
+	const insn_byte_t *end_kaddr;	/* kernel address of last insn in buffer */
+	const insn_byte_t *next_byte;
+};
+
+#define MAX_INSN_SIZE	15
+
+#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
+#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
+#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
+
+#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
+#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
+#define X86_SIB_BASE(sib) ((sib) & 0x07)
+
+#define X86_REX_W(rex) ((rex) & 8)
+#define X86_REX_R(rex) ((rex) & 4)
+#define X86_REX_X(rex) ((rex) & 2)
+#define X86_REX_B(rex) ((rex) & 1)
+
+/* VEX bit flags  */
+#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
+#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
+#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
+#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
+#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
+/* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
+#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
+#define X86_VEX2_M	1			/* VEX2.M always 1 */
+#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
+
+extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
+extern void insn_get_prefixes(struct insn *insn);
+extern void insn_get_opcode(struct insn *insn);
+extern void insn_get_modrm(struct insn *insn);
+extern void insn_get_sib(struct insn *insn);
+extern void insn_get_displacement(struct insn *insn);
+extern void insn_get_immediate(struct insn *insn);
+extern void insn_get_length(struct insn *insn);
+
+/* Attribute will be determined after getting ModRM (for opcode groups) */
+static inline void insn_get_attribute(struct insn *insn)
+{
+	insn_get_modrm(insn);
+}
+
+/* Instruction uses RIP-relative addressing */
+extern int insn_rip_relative(struct insn *insn);
+
+/* Init insn for kernel text */
+static inline void kernel_insn_init(struct insn *insn,
+				    const void *kaddr, int buf_len)
+{
+#ifdef CONFIG_X86_64
+	insn_init(insn, kaddr, buf_len, 1);
+#else /* CONFIG_X86_32 */
+	insn_init(insn, kaddr, buf_len, 0);
+#endif
+}
+
+static inline int insn_is_avx(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.value != 0);
+}
+
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+		insn->displacement.got && insn->immediate.got;
+}
+
+static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX2_M;
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
+		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
+}
+
+static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX_P(insn->vex_prefix.bytes[1]);
+	else
+		return X86_VEX_P(insn->vex_prefix.bytes[2]);
+}
+
+/* Get the last prefix id from last prefix or VEX prefix */
+static inline int insn_last_prefix_id(struct insn *insn)
+{
+	if (insn_is_avx(insn))
+		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
+
+	if (insn->prefixes.bytes[3])
+		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
+
+	return 0;
+}
+
+/* Offset of each field from kaddr */
+static inline int insn_offset_rex_prefix(struct insn *insn)
+{
+	return insn->prefixes.nbytes;
+}
+static inline int insn_offset_vex_prefix(struct insn *insn)
+{
+	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
+}
+static inline int insn_offset_opcode(struct insn *insn)
+{
+	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
+}
+static inline int insn_offset_modrm(struct insn *insn)
+{
+	return insn_offset_opcode(insn) + insn->opcode.nbytes;
+}
+static inline int insn_offset_sib(struct insn *insn)
+{
+	return insn_offset_modrm(insn) + insn->modrm.nbytes;
+}
+static inline int insn_offset_displacement(struct insn *insn)
+{
+	return insn_offset_sib(insn) + insn->sib.nbytes;
+}
+static inline int insn_offset_immediate(struct insn *insn)
+{
+	return insn_offset_displacement(insn) + insn->displacement.nbytes;
+}
+
+#endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
new file mode 100644
index 000000000000..9c9dc579bd7d
--- /dev/null
+++ b/tools/objtool/arch/x86/include/asm/orc_types.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ORC_TYPES_H
+#define _ORC_TYPES_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+/*
+ * The ORC_REG_* registers are base registers which are used to find other
+ * registers on the stack.
+ *
+ * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
+ * address of the previous frame: the caller's SP before it called the current
+ * function.
+ *
+ * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
+ * the current frame.
+ *
+ * The most commonly used base registers are SP and BP -- which the previous SP
+ * is usually based on -- and PREV_SP and UNDEFINED -- which the previous BP is
+ * usually based on.
+ *
+ * The rest of the base registers are needed for special cases like entry code
+ * and GCC realigned stacks.
+ */
+#define ORC_REG_UNDEFINED		0
+#define ORC_REG_PREV_SP			1
+#define ORC_REG_DX			2
+#define ORC_REG_DI			3
+#define ORC_REG_BP			4
+#define ORC_REG_SP			5
+#define ORC_REG_R10			6
+#define ORC_REG_R13			7
+#define ORC_REG_BP_INDIRECT		8
+#define ORC_REG_SP_INDIRECT		9
+#define ORC_REG_MAX			15
+
+/*
+ * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
+ * caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
+ * to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
+ * points to the iret return frame.
+ *
+ * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
+ * aren't used in struct orc_entry due to size and complexity constraints.
+ * Objtool converts them to real types when it converts the hints to orc
+ * entries.
+ */
+#define ORC_TYPE_CALL			0
+#define ORC_TYPE_REGS			1
+#define ORC_TYPE_REGS_IRET		2
+#define UNWIND_HINT_TYPE_SAVE		3
+#define UNWIND_HINT_TYPE_RESTORE	4
+
+#ifndef __ASSEMBLY__
+/*
+ * This struct is more or less a vastly simplified version of the DWARF Call
+ * Frame Information standard.  It contains only the necessary parts of DWARF
+ * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
+ * unwinder how to find the previous SP and BP (and sometimes entry regs) on
+ * the stack for a given code address.  Each instance of the struct corresponds
+ * to one or more code locations.
+ */
+struct orc_entry {
+	s16		sp_offset;
+	s16		bp_offset;
+	unsigned	sp_reg:4;
+	unsigned	bp_reg:4;
+	unsigned	type:2;
+} __packed;
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack for the ORC unwinder.
+ *
+ * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+};
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ORC_TYPES_H */
diff --git a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
deleted file mode 100644
index b02a36b2c14f..000000000000
--- a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
+++ /dev/null
@@ -1,393 +0,0 @@
-#!/bin/awk -f
-# SPDX-License-Identifier: GPL-2.0
-# gen-insn-attr-x86.awk: Instruction attribute table generator
-# Written by Masami Hiramatsu <mhiramat@redhat.com>
-#
-# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
-
-# Awk implementation sanity check
-function check_awk_implement() {
-	if (sprintf("%x", 0) != "0")
-		return "Your awk has a printf-format problem."
-	return ""
-}
-
-# Clear working vars
-function clear_vars() {
-	delete table
-	delete lptable2
-	delete lptable1
-	delete lptable3
-	eid = -1 # escape id
-	gid = -1 # group id
-	aid = -1 # AVX id
-	tname = ""
-}
-
-BEGIN {
-	# Implementation error checking
-	awkchecked = check_awk_implement()
-	if (awkchecked != "") {
-		print "Error: " awkchecked > "/dev/stderr"
-		print "Please try to use gawk." > "/dev/stderr"
-		exit 1
-	}
-
-	# Setup generating tables
-	print "/* x86 opcode map generated from x86-opcode-map.txt */"
-	print "/* Do not change this code. */\n"
-	ggid = 1
-	geid = 1
-	gaid = 0
-	delete etable
-	delete gtable
-	delete atable
-
-	opnd_expr = "^[A-Za-z/]"
-	ext_expr = "^\\("
-	sep_expr = "^\\|$"
-	group_expr = "^Grp[0-9A-Za-z]+"
-
-	imm_expr = "^[IJAOL][a-z]"
-	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
-	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
-	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
-	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
-	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
-	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
-	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
-	imm_flag["Ob"] = "INAT_MOFFSET"
-	imm_flag["Ov"] = "INAT_MOFFSET"
-	imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-
-	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
-	force64_expr = "\\([df]64\\)"
-	rex_expr = "^REX(\\.[XRWB]+)*"
-	fpu_expr = "^ESC" # TODO
-
-	lprefix1_expr = "\\((66|!F3)\\)"
-	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
-	lprefix_expr = "\\((66|F2|F3)\\)"
-	max_lprefix = 4
-
-	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
-	# accepts VEX prefix
-	vexok_opcode_expr = "^[vk].*"
-	vexok_expr = "\\(v1\\)"
-	# All opcodes with (v) superscript supports *only* VEX prefix
-	vexonly_expr = "\\(v\\)"
-	# All opcodes with (ev) superscript supports *only* EVEX prefix
-	evexonly_expr = "\\(ev\\)"
-
-	prefix_expr = "\\(Prefix\\)"
-	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
-	prefix_num["REPNE"] = "INAT_PFX_REPNE"
-	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
-	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
-	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
-	prefix_num["LOCK"] = "INAT_PFX_LOCK"
-	prefix_num["SEG=CS"] = "INAT_PFX_CS"
-	prefix_num["SEG=DS"] = "INAT_PFX_DS"
-	prefix_num["SEG=ES"] = "INAT_PFX_ES"
-	prefix_num["SEG=FS"] = "INAT_PFX_FS"
-	prefix_num["SEG=GS"] = "INAT_PFX_GS"
-	prefix_num["SEG=SS"] = "INAT_PFX_SS"
-	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
-	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
-	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
-	prefix_num["EVEX"] = "INAT_PFX_EVEX"
-
-	clear_vars()
-}
-
-function semantic_error(msg) {
-	print "Semantic error at " NR ": " msg > "/dev/stderr"
-	exit 1
-}
-
-function debug(msg) {
-	print "DEBUG: " msg
-}
-
-function array_size(arr,   i,c) {
-	c = 0
-	for (i in arr)
-		c++
-	return c
-}
-
-/^Table:/ {
-	print "/* " $0 " */"
-	if (tname != "")
-		semantic_error("Hit Table: before EndTable:.");
-}
-
-/^Referrer:/ {
-	if (NF != 1) {
-		# escape opcode table
-		ref = ""
-		for (i = 2; i <= NF; i++)
-			ref = ref $i
-		eid = escape[ref]
-		tname = sprintf("inat_escape_table_%d", eid)
-	}
-}
-
-/^AVXcode:/ {
-	if (NF != 1) {
-		# AVX/escape opcode table
-		aid = $2
-		if (gaid <= aid)
-			gaid = aid + 1
-		if (tname == "")	# AVX only opcode table
-			tname = sprintf("inat_avx_table_%d", $2)
-	}
-	if (aid == -1 && eid == -1)	# primary opcode table
-		tname = "inat_primary_table"
-}
-
-/^GrpTable:/ {
-	print "/* " $0 " */"
-	if (!($2 in group))
-		semantic_error("No group: " $2 )
-	gid = group[$2]
-	tname = "inat_group_table_" gid
-}
-
-function print_table(tbl,name,fmt,n)
-{
-	print "const insn_attr_t " name " = {"
-	for (i = 0; i < n; i++) {
-		id = sprintf(fmt, i)
-		if (tbl[id])
-			print "	[" id "] = " tbl[id] ","
-	}
-	print "};"
-}
-
-/^EndTable/ {
-	if (gid != -1) {
-		# print group tables
-		if (array_size(table) != 0) {
-			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,0] = tname
-		}
-		if (array_size(lptable1) != 0) {
-			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,1] = tname "_1"
-		}
-		if (array_size(lptable2) != 0) {
-			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,2] = tname "_2"
-		}
-		if (array_size(lptable3) != 0) {
-			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,3] = tname "_3"
-		}
-	} else {
-		# print primary/escaped tables
-		if (array_size(table) != 0) {
-			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,0] = tname
-			if (aid >= 0)
-				atable[aid,0] = tname
-		}
-		if (array_size(lptable1) != 0) {
-			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,1] = tname "_1"
-			if (aid >= 0)
-				atable[aid,1] = tname "_1"
-		}
-		if (array_size(lptable2) != 0) {
-			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,2] = tname "_2"
-			if (aid >= 0)
-				atable[aid,2] = tname "_2"
-		}
-		if (array_size(lptable3) != 0) {
-			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,3] = tname "_3"
-			if (aid >= 0)
-				atable[aid,3] = tname "_3"
-		}
-	}
-	print ""
-	clear_vars()
-}
-
-function add_flags(old,new) {
-	if (old && new)
-		return old " | " new
-	else if (old)
-		return old
-	else
-		return new
-}
-
-# convert operands to flags.
-function convert_operands(count,opnd,       i,j,imm,mod)
-{
-	imm = null
-	mod = null
-	for (j = 1; j <= count; j++) {
-		i = opnd[j]
-		if (match(i, imm_expr) == 1) {
-			if (!imm_flag[i])
-				semantic_error("Unknown imm opnd: " i)
-			if (imm) {
-				if (i != "Ib")
-					semantic_error("Second IMM error")
-				imm = add_flags(imm, "INAT_SCNDIMM")
-			} else
-				imm = imm_flag[i]
-		} else if (match(i, modrm_expr))
-			mod = "INAT_MODRM"
-	}
-	return add_flags(imm, mod)
-}
-
-/^[0-9a-f]+\:/ {
-	if (NR == 1)
-		next
-	# get index
-	idx = "0x" substr($1, 1, index($1,":") - 1)
-	if (idx in table)
-		semantic_error("Redefine " idx " in " tname)
-
-	# check if escaped opcode
-	if ("escape" == $2) {
-		if ($3 != "#")
-			semantic_error("No escaped name")
-		ref = ""
-		for (i = 4; i <= NF; i++)
-			ref = ref $i
-		if (ref in escape)
-			semantic_error("Redefine escape (" ref ")")
-		escape[ref] = geid
-		geid++
-		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
-		next
-	}
-
-	variant = null
-	# converts
-	i = 2
-	while (i <= NF) {
-		opcode = $(i++)
-		delete opnds
-		ext = null
-		flags = null
-		opnd = null
-		# parse one opcode
-		if (match($i, opnd_expr)) {
-			opnd = $i
-			count = split($(i++), opnds, ",")
-			flags = convert_operands(count, opnds)
-		}
-		if (match($i, ext_expr))
-			ext = $(i++)
-		if (match($i, sep_expr))
-			i++
-		else if (i < NF)
-			semantic_error($i " is not a separator")
-
-		# check if group opcode
-		if (match(opcode, group_expr)) {
-			if (!(opcode in group)) {
-				group[opcode] = ggid
-				ggid++
-			}
-			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
-		}
-		# check force(or default) 64bit
-		if (match(ext, force64_expr))
-			flags = add_flags(flags, "INAT_FORCE64")
-
-		# check REX prefix
-		if (match(opcode, rex_expr))
-			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
-
-		# check coprocessor escape : TODO
-		if (match(opcode, fpu_expr))
-			flags = add_flags(flags, "INAT_MODRM")
-
-		# check VEX codes
-		if (match(ext, evexonly_expr))
-			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
-		else if (match(ext, vexonly_expr))
-			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
-		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
-			flags = add_flags(flags, "INAT_VEXOK")
-
-		# check prefixes
-		if (match(ext, prefix_expr)) {
-			if (!prefix_num[opcode])
-				semantic_error("Unknown prefix: " opcode)
-			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
-		}
-		if (length(flags) == 0)
-			continue
-		# check if last prefix
-		if (match(ext, lprefix1_expr)) {
-			lptable1[idx] = add_flags(lptable1[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (match(ext, lprefix2_expr)) {
-			lptable2[idx] = add_flags(lptable2[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (match(ext, lprefix3_expr)) {
-			lptable3[idx] = add_flags(lptable3[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (!match(ext, lprefix_expr)){
-			table[idx] = add_flags(table[idx],flags)
-		}
-	}
-	if (variant)
-		table[idx] = add_flags(table[idx],variant)
-}
-
-END {
-	if (awkchecked != "")
-		exit 1
-	# print escape opcode map's array
-	print "/* Escape opcode map array */"
-	print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < geid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (etable[i,j])
-				print "	["i"]["j"] = "etable[i,j]","
-	print "};\n"
-	# print group opcode map's array
-	print "/* Group opcode map array */"
-	print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < ggid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (gtable[i,j])
-				print "	["i"]["j"] = "gtable[i,j]","
-	print "};\n"
-	# print AVX opcode map's array
-	print "/* AVX opcode map array */"
-	print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < gaid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (atable[i,j])
-				print "	["i"]["j"] = "atable[i,j]","
-	print "};"
-}
-
diff --git a/tools/objtool/arch/x86/insn/inat.c b/tools/objtool/arch/x86/insn/inat.c
deleted file mode 100644
index e4bf28e6f4c7..000000000000
--- a/tools/objtool/arch/x86/insn/inat.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * x86 instruction attribute tables
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- */
-#include "insn.h"
-
-/* Attribute tables are generated from opcode map */
-#include "inat-tables.c"
-
-/* Attribute search APIs */
-insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
-{
-	return inat_primary_table[opcode];
-}
-
-int inat_get_last_prefix_id(insn_byte_t last_pfx)
-{
-	insn_attr_t lpfx_attr;
-
-	lpfx_attr = inat_get_opcode_attribute(last_pfx);
-	return inat_last_prefix_id(lpfx_attr);
-}
-
-insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
-				      insn_attr_t esc_attr)
-{
-	const insn_attr_t *table;
-	int n;
-
-	n = inat_escape_id(esc_attr);
-
-	table = inat_escape_tables[n][0];
-	if (!table)
-		return 0;
-	if (inat_has_variant(table[opcode]) && lpfx_id) {
-		table = inat_escape_tables[n][lpfx_id];
-		if (!table)
-			return 0;
-	}
-	return table[opcode];
-}
-
-insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
-				     insn_attr_t grp_attr)
-{
-	const insn_attr_t *table;
-	int n;
-
-	n = inat_group_id(grp_attr);
-
-	table = inat_group_tables[n][0];
-	if (!table)
-		return inat_group_common_attribute(grp_attr);
-	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
-		table = inat_group_tables[n][lpfx_id];
-		if (!table)
-			return inat_group_common_attribute(grp_attr);
-	}
-	return table[X86_MODRM_REG(modrm)] |
-	       inat_group_common_attribute(grp_attr);
-}
-
-insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
-				   insn_byte_t vex_p)
-{
-	const insn_attr_t *table;
-	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
-		return 0;
-	/* At first, this checks the master table */
-	table = inat_avx_tables[vex_m][0];
-	if (!table)
-		return 0;
-	if (!inat_is_group(table[opcode]) && vex_p) {
-		/* If this is not a group, get attribute directly */
-		table = inat_avx_tables[vex_m][vex_p];
-		if (!table)
-			return 0;
-	}
-	return table[opcode];
-}
-
diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/insn/inat.h
deleted file mode 100644
index 125ecd2a300d..000000000000
--- a/tools/objtool/arch/x86/insn/inat.h
+++ /dev/null
@@ -1,234 +0,0 @@
-#ifndef _ASM_X86_INAT_H
-#define _ASM_X86_INAT_H
-/*
- * x86 instruction attributes
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- */
-#include "inat_types.h"
-
-/*
- * Internal bits. Don't use bitmasks directly, because these bits are
- * unstable. You should use checking functions.
- */
-
-#define INAT_OPCODE_TABLE_SIZE 256
-#define INAT_GROUP_TABLE_SIZE 8
-
-/* Legacy last prefixes */
-#define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
-#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
-#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
-/* Other Legacy prefixes */
-#define INAT_PFX_LOCK	4	/* 0xF0 */
-#define INAT_PFX_CS	5	/* 0x2E */
-#define INAT_PFX_DS	6	/* 0x3E */
-#define INAT_PFX_ES	7	/* 0x26 */
-#define INAT_PFX_FS	8	/* 0x64 */
-#define INAT_PFX_GS	9	/* 0x65 */
-#define INAT_PFX_SS	10	/* 0x36 */
-#define INAT_PFX_ADDRSZ	11	/* 0x67 */
-/* x86-64 REX prefix */
-#define INAT_PFX_REX	12	/* 0x4X */
-/* AVX VEX prefixes */
-#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
-#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
-#define INAT_PFX_EVEX	15	/* EVEX prefix */
-
-#define INAT_LSTPFX_MAX	3
-#define INAT_LGCPFX_MAX	11
-
-/* Immediate size */
-#define INAT_IMM_BYTE		1
-#define INAT_IMM_WORD		2
-#define INAT_IMM_DWORD		3
-#define INAT_IMM_QWORD		4
-#define INAT_IMM_PTR		5
-#define INAT_IMM_VWORD32	6
-#define INAT_IMM_VWORD		7
-
-/* Legacy prefix */
-#define INAT_PFX_OFFS	0
-#define INAT_PFX_BITS	4
-#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
-#define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
-/* Escape opcodes */
-#define INAT_ESC_OFFS	(INAT_PFX_OFFS + INAT_PFX_BITS)
-#define INAT_ESC_BITS	2
-#define INAT_ESC_MAX	((1 << INAT_ESC_BITS) - 1)
-#define INAT_ESC_MASK	(INAT_ESC_MAX << INAT_ESC_OFFS)
-/* Group opcodes (1-16) */
-#define INAT_GRP_OFFS	(INAT_ESC_OFFS + INAT_ESC_BITS)
-#define INAT_GRP_BITS	5
-#define INAT_GRP_MAX	((1 << INAT_GRP_BITS) - 1)
-#define INAT_GRP_MASK	(INAT_GRP_MAX << INAT_GRP_OFFS)
-/* Immediates */
-#define INAT_IMM_OFFS	(INAT_GRP_OFFS + INAT_GRP_BITS)
-#define INAT_IMM_BITS	3
-#define INAT_IMM_MASK	(((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
-/* Flags */
-#define INAT_FLAG_OFFS	(INAT_IMM_OFFS + INAT_IMM_BITS)
-#define INAT_MODRM	(1 << (INAT_FLAG_OFFS))
-#define INAT_FORCE64	(1 << (INAT_FLAG_OFFS + 1))
-#define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
-#define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
-#define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
-#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
-#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
-#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
-/* Attribute making macros for attribute tables */
-#define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
-#define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
-#define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
-#define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
-
-/* Attribute search APIs */
-extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
-extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
-extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     int lpfx_id,
-					     insn_attr_t esc_attr);
-extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    int lpfx_id,
-					    insn_attr_t esc_attr);
-extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
-					  insn_byte_t vex_m,
-					  insn_byte_t vex_pp);
-
-/* Attribute checking functions */
-static inline int inat_is_legacy_prefix(insn_attr_t attr)
-{
-	attr &= INAT_PFX_MASK;
-	return attr && attr <= INAT_LGCPFX_MAX;
-}
-
-static inline int inat_is_address_size_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
-}
-
-static inline int inat_is_operand_size_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
-}
-
-static inline int inat_is_rex_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
-}
-
-static inline int inat_last_prefix_id(insn_attr_t attr)
-{
-	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
-		return 0;
-	else
-		return attr & INAT_PFX_MASK;
-}
-
-static inline int inat_is_vex_prefix(insn_attr_t attr)
-{
-	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
-	       attr == INAT_PFX_EVEX;
-}
-
-static inline int inat_is_evex_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
-}
-
-static inline int inat_is_vex3_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
-}
-
-static inline int inat_is_escape(insn_attr_t attr)
-{
-	return attr & INAT_ESC_MASK;
-}
-
-static inline int inat_escape_id(insn_attr_t attr)
-{
-	return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
-}
-
-static inline int inat_is_group(insn_attr_t attr)
-{
-	return attr & INAT_GRP_MASK;
-}
-
-static inline int inat_group_id(insn_attr_t attr)
-{
-	return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
-}
-
-static inline int inat_group_common_attribute(insn_attr_t attr)
-{
-	return attr & ~INAT_GRP_MASK;
-}
-
-static inline int inat_has_immediate(insn_attr_t attr)
-{
-	return attr & INAT_IMM_MASK;
-}
-
-static inline int inat_immediate_size(insn_attr_t attr)
-{
-	return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
-}
-
-static inline int inat_has_modrm(insn_attr_t attr)
-{
-	return attr & INAT_MODRM;
-}
-
-static inline int inat_is_force64(insn_attr_t attr)
-{
-	return attr & INAT_FORCE64;
-}
-
-static inline int inat_has_second_immediate(insn_attr_t attr)
-{
-	return attr & INAT_SCNDIMM;
-}
-
-static inline int inat_has_moffset(insn_attr_t attr)
-{
-	return attr & INAT_MOFFSET;
-}
-
-static inline int inat_has_variant(insn_attr_t attr)
-{
-	return attr & INAT_VARIANT;
-}
-
-static inline int inat_accept_vex(insn_attr_t attr)
-{
-	return attr & INAT_VEXOK;
-}
-
-static inline int inat_must_vex(insn_attr_t attr)
-{
-	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
-}
-
-static inline int inat_must_evex(insn_attr_t attr)
-{
-	return attr & INAT_EVEXONLY;
-}
-#endif
diff --git a/tools/objtool/arch/x86/insn/inat_types.h b/tools/objtool/arch/x86/insn/inat_types.h
deleted file mode 100644
index cb3c20ce39cf..000000000000
--- a/tools/objtool/arch/x86/insn/inat_types.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _ASM_X86_INAT_TYPES_H
-#define _ASM_X86_INAT_TYPES_H
-/*
- * x86 instruction attributes
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- */
-
-/* Instruction attributes */
-typedef unsigned int insn_attr_t;
-typedef unsigned char insn_byte_t;
-typedef signed int insn_value_t;
-
-#endif
diff --git a/tools/objtool/arch/x86/insn/insn.c b/tools/objtool/arch/x86/insn/insn.c
deleted file mode 100644
index ca983e2bea8b..000000000000
--- a/tools/objtool/arch/x86/insn/insn.c
+++ /dev/null
@@ -1,606 +0,0 @@
-/*
- * x86 instruction analysis
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2002, 2004, 2009
- */
-
-#ifdef __KERNEL__
-#include <linux/string.h>
-#else
-#include <string.h>
-#endif
-#include "inat.h"
-#include "insn.h"
-
-/* Verify next sizeof(t) bytes can be on the same instruction */
-#define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
-
-#define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
-
-#define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); r; })
-
-#define get_next(t, insn)	\
-	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
-
-#define peek_nbyte_next(t, insn, n)	\
-	({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); })
-
-#define peek_next(t, insn)	peek_nbyte_next(t, insn, 0)
-
-/**
- * insn_init() - initialize struct insn
- * @insn:	&struct insn to be initialized
- * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
- * @x86_64:	!0 for 64-bit kernel or 64-bit app
- */
-void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
-{
-	/*
-	 * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid
-	 * even if the input buffer is long enough to hold them.
-	 */
-	if (buf_len > MAX_INSN_SIZE)
-		buf_len = MAX_INSN_SIZE;
-
-	memset(insn, 0, sizeof(*insn));
-	insn->kaddr = kaddr;
-	insn->end_kaddr = kaddr + buf_len;
-	insn->next_byte = kaddr;
-	insn->x86_64 = x86_64 ? 1 : 0;
-	insn->opnd_bytes = 4;
-	if (x86_64)
-		insn->addr_bytes = 8;
-	else
-		insn->addr_bytes = 4;
-}
-
-/**
- * insn_get_prefixes - scan x86 instruction prefix bytes
- * @insn:	&struct insn containing instruction
- *
- * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
- * to point to the (first) opcode.  No effect if @insn->prefixes.got
- * is already set.
- */
-void insn_get_prefixes(struct insn *insn)
-{
-	struct insn_field *prefixes = &insn->prefixes;
-	insn_attr_t attr;
-	insn_byte_t b, lb;
-	int i, nb;
-
-	if (prefixes->got)
-		return;
-
-	nb = 0;
-	lb = 0;
-	b = peek_next(insn_byte_t, insn);
-	attr = inat_get_opcode_attribute(b);
-	while (inat_is_legacy_prefix(attr)) {
-		/* Skip if same prefix */
-		for (i = 0; i < nb; i++)
-			if (prefixes->bytes[i] == b)
-				goto found;
-		if (nb == 4)
-			/* Invalid instruction */
-			break;
-		prefixes->bytes[nb++] = b;
-		if (inat_is_address_size_prefix(attr)) {
-			/* address size switches 2/4 or 4/8 */
-			if (insn->x86_64)
-				insn->addr_bytes ^= 12;
-			else
-				insn->addr_bytes ^= 6;
-		} else if (inat_is_operand_size_prefix(attr)) {
-			/* oprand size switches 2/4 */
-			insn->opnd_bytes ^= 6;
-		}
-found:
-		prefixes->nbytes++;
-		insn->next_byte++;
-		lb = b;
-		b = peek_next(insn_byte_t, insn);
-		attr = inat_get_opcode_attribute(b);
-	}
-	/* Set the last prefix */
-	if (lb && lb != insn->prefixes.bytes[3]) {
-		if (unlikely(insn->prefixes.bytes[3])) {
-			/* Swap the last prefix */
-			b = insn->prefixes.bytes[3];
-			for (i = 0; i < nb; i++)
-				if (prefixes->bytes[i] == lb)
-					prefixes->bytes[i] = b;
-		}
-		insn->prefixes.bytes[3] = lb;
-	}
-
-	/* Decode REX prefix */
-	if (insn->x86_64) {
-		b = peek_next(insn_byte_t, insn);
-		attr = inat_get_opcode_attribute(b);
-		if (inat_is_rex_prefix(attr)) {
-			insn->rex_prefix.value = b;
-			insn->rex_prefix.nbytes = 1;
-			insn->next_byte++;
-			if (X86_REX_W(b))
-				/* REX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		}
-	}
-	insn->rex_prefix.got = 1;
-
-	/* Decode VEX prefix */
-	b = peek_next(insn_byte_t, insn);
-	attr = inat_get_opcode_attribute(b);
-	if (inat_is_vex_prefix(attr)) {
-		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
-		if (!insn->x86_64) {
-			/*
-			 * In 32-bits mode, if the [7:6] bits (mod bits of
-			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES or BOUND.
-			 */
-			if (X86_MODRM_MOD(b2) != 3)
-				goto vex_end;
-		}
-		insn->vex_prefix.bytes[0] = b;
-		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_evex_prefix(attr)) {
-			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
-			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
-			insn->vex_prefix.bytes[3] = b2;
-			insn->vex_prefix.nbytes = 4;
-			insn->next_byte += 4;
-			if (insn->x86_64 && X86_VEX_W(b2))
-				/* VEX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		} else if (inat_is_vex3_prefix(attr)) {
-			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
-			insn->vex_prefix.nbytes = 3;
-			insn->next_byte += 3;
-			if (insn->x86_64 && X86_VEX_W(b2))
-				/* VEX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		} else {
-			/*
-			 * For VEX2, fake VEX3-like byte#2.
-			 * Makes it easier to decode vex.W, vex.vvvv,
-			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
-			 */
-			insn->vex_prefix.bytes[2] = b2 & 0x7f;
-			insn->vex_prefix.nbytes = 2;
-			insn->next_byte += 2;
-		}
-	}
-vex_end:
-	insn->vex_prefix.got = 1;
-
-	prefixes->got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_opcode - collect opcode(s)
- * @insn:	&struct insn containing instruction
- *
- * Populates @insn->opcode, updates @insn->next_byte to point past the
- * opcode byte(s), and set @insn->attr (except for groups).
- * If necessary, first collects any preceding (prefix) bytes.
- * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
- * is already 1.
- */
-void insn_get_opcode(struct insn *insn)
-{
-	struct insn_field *opcode = &insn->opcode;
-	insn_byte_t op;
-	int pfx_id;
-	if (opcode->got)
-		return;
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-
-	/* Get first opcode */
-	op = get_next(insn_byte_t, insn);
-	opcode->bytes[0] = op;
-	opcode->nbytes = 1;
-
-	/* Check if there is VEX prefix or not */
-	if (insn_is_avx(insn)) {
-		insn_byte_t m, p;
-		m = insn_vex_m_bits(insn);
-		p = insn_vex_p_bits(insn);
-		insn->attr = inat_get_avx_attribute(op, m, p);
-		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
-		    (!inat_accept_vex(insn->attr) &&
-		     !inat_is_group(insn->attr)))
-			insn->attr = 0;	/* This instruction is bad */
-		goto end;	/* VEX has only 1 byte for opcode */
-	}
-
-	insn->attr = inat_get_opcode_attribute(op);
-	while (inat_is_escape(insn->attr)) {
-		/* Get escaped opcode */
-		op = get_next(insn_byte_t, insn);
-		opcode->bytes[opcode->nbytes++] = op;
-		pfx_id = insn_last_prefix_id(insn);
-		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
-	}
-	if (inat_must_vex(insn->attr))
-		insn->attr = 0;	/* This instruction is bad */
-end:
-	opcode->got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_modrm - collect ModRM byte, if any
- * @insn:	&struct insn containing instruction
- *
- * Populates @insn->modrm and updates @insn->next_byte to point past the
- * ModRM byte, if any.  If necessary, first collects the preceding bytes
- * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
- */
-void insn_get_modrm(struct insn *insn)
-{
-	struct insn_field *modrm = &insn->modrm;
-	insn_byte_t pfx_id, mod;
-	if (modrm->got)
-		return;
-	if (!insn->opcode.got)
-		insn_get_opcode(insn);
-
-	if (inat_has_modrm(insn->attr)) {
-		mod = get_next(insn_byte_t, insn);
-		modrm->value = mod;
-		modrm->nbytes = 1;
-		if (inat_is_group(insn->attr)) {
-			pfx_id = insn_last_prefix_id(insn);
-			insn->attr = inat_get_group_attribute(mod, pfx_id,
-							      insn->attr);
-			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
-				insn->attr = 0;	/* This is bad */
-		}
-	}
-
-	if (insn->x86_64 && inat_is_force64(insn->attr))
-		insn->opnd_bytes = 8;
-	modrm->got = 1;
-
-err_out:
-	return;
-}
-
-
-/**
- * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * ModRM byte.  No effect if @insn->x86_64 is 0.
- */
-int insn_rip_relative(struct insn *insn)
-{
-	struct insn_field *modrm = &insn->modrm;
-
-	if (!insn->x86_64)
-		return 0;
-	if (!modrm->got)
-		insn_get_modrm(insn);
-	/*
-	 * For rip-relative instructions, the mod field (top 2 bits)
-	 * is zero and the r/m field (bottom 3 bits) is 0x5.
-	 */
-	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
-}
-
-/**
- * insn_get_sib() - Get the SIB byte of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * ModRM byte.
- */
-void insn_get_sib(struct insn *insn)
-{
-	insn_byte_t modrm;
-
-	if (insn->sib.got)
-		return;
-	if (!insn->modrm.got)
-		insn_get_modrm(insn);
-	if (insn->modrm.nbytes) {
-		modrm = (insn_byte_t)insn->modrm.value;
-		if (insn->addr_bytes != 2 &&
-		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
-			insn->sib.value = get_next(insn_byte_t, insn);
-			insn->sib.nbytes = 1;
-		}
-	}
-	insn->sib.got = 1;
-
-err_out:
-	return;
-}
-
-
-/**
- * insn_get_displacement() - Get the displacement of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * SIB byte.
- * Displacement value is sign-expanded.
- */
-void insn_get_displacement(struct insn *insn)
-{
-	insn_byte_t mod, rm, base;
-
-	if (insn->displacement.got)
-		return;
-	if (!insn->sib.got)
-		insn_get_sib(insn);
-	if (insn->modrm.nbytes) {
-		/*
-		 * Interpreting the modrm byte:
-		 * mod = 00 - no displacement fields (exceptions below)
-		 * mod = 01 - 1-byte displacement field
-		 * mod = 10 - displacement field is 4 bytes, or 2 bytes if
-		 * 	address size = 2 (0x67 prefix in 32-bit mode)
-		 * mod = 11 - no memory operand
-		 *
-		 * If address size = 2...
-		 * mod = 00, r/m = 110 - displacement field is 2 bytes
-		 *
-		 * If address size != 2...
-		 * mod != 11, r/m = 100 - SIB byte exists
-		 * mod = 00, SIB base = 101 - displacement field is 4 bytes
-		 * mod = 00, r/m = 101 - rip-relative addressing, displacement
-		 * 	field is 4 bytes
-		 */
-		mod = X86_MODRM_MOD(insn->modrm.value);
-		rm = X86_MODRM_RM(insn->modrm.value);
-		base = X86_SIB_BASE(insn->sib.value);
-		if (mod == 3)
-			goto out;
-		if (mod == 1) {
-			insn->displacement.value = get_next(signed char, insn);
-			insn->displacement.nbytes = 1;
-		} else if (insn->addr_bytes == 2) {
-			if ((mod == 0 && rm == 6) || mod == 2) {
-				insn->displacement.value =
-					 get_next(short, insn);
-				insn->displacement.nbytes = 2;
-			}
-		} else {
-			if ((mod == 0 && rm == 5) || mod == 2 ||
-			    (mod == 0 && base == 5)) {
-				insn->displacement.value = get_next(int, insn);
-				insn->displacement.nbytes = 4;
-			}
-		}
-	}
-out:
-	insn->displacement.got = 1;
-
-err_out:
-	return;
-}
-
-/* Decode moffset16/32/64. Return 0 if failed */
-static int __get_moffset(struct insn *insn)
-{
-	switch (insn->addr_bytes) {
-	case 2:
-		insn->moffset1.value = get_next(short, insn);
-		insn->moffset1.nbytes = 2;
-		break;
-	case 4:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		break;
-	case 8:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		insn->moffset2.value = get_next(int, insn);
-		insn->moffset2.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->moffset1.got = insn->moffset2.got = 1;
-
-	return 1;
-
-err_out:
-	return 0;
-}
-
-/* Decode imm v32(Iz). Return 0 if failed */
-static int __get_immv32(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
-		break;
-	case 4:
-	case 8:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-
-	return 1;
-
-err_out:
-	return 0;
-}
-
-/* Decode imm v64(Iv/Ov), Return 0 if failed */
-static int __get_immv(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
-		break;
-	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		break;
-	case 8:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->immediate1.got = insn->immediate2.got = 1;
-
-	return 1;
-err_out:
-	return 0;
-}
-
-/* Decode ptr16:16/32(Ap) */
-static int __get_immptr(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
-		break;
-	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		break;
-	case 8:
-		/* ptr16:64 is not exist (no segment) */
-		return 0;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->immediate2.value = get_next(unsigned short, insn);
-	insn->immediate2.nbytes = 2;
-	insn->immediate1.got = insn->immediate2.got = 1;
-
-	return 1;
-err_out:
-	return 0;
-}
-
-/**
- * insn_get_immediate() - Get the immediates of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * displacement bytes.
- * Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
- */
-void insn_get_immediate(struct insn *insn)
-{
-	if (insn->immediate.got)
-		return;
-	if (!insn->displacement.got)
-		insn_get_displacement(insn);
-
-	if (inat_has_moffset(insn->attr)) {
-		if (!__get_moffset(insn))
-			goto err_out;
-		goto done;
-	}
-
-	if (!inat_has_immediate(insn->attr))
-		/* no immediates */
-		goto done;
-
-	switch (inat_immediate_size(insn->attr)) {
-	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(signed char, insn);
-		insn->immediate.nbytes = 1;
-		break;
-	case INAT_IMM_WORD:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
-		break;
-	case INAT_IMM_DWORD:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
-		break;
-	case INAT_IMM_QWORD:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
-		break;
-	case INAT_IMM_PTR:
-		if (!__get_immptr(insn))
-			goto err_out;
-		break;
-	case INAT_IMM_VWORD32:
-		if (!__get_immv32(insn))
-			goto err_out;
-		break;
-	case INAT_IMM_VWORD:
-		if (!__get_immv(insn))
-			goto err_out;
-		break;
-	default:
-		/* Here, insn must have an immediate, but failed */
-		goto err_out;
-	}
-	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(signed char, insn);
-		insn->immediate2.nbytes = 1;
-	}
-done:
-	insn->immediate.got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_length() - Get the length of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * immediates bytes.
- */
-void insn_get_length(struct insn *insn)
-{
-	if (insn->length)
-		return;
-	if (!insn->immediate.got)
-		insn_get_immediate(insn);
-	insn->length = (unsigned char)((unsigned long)insn->next_byte
-				     - (unsigned long)insn->kaddr);
-}
diff --git a/tools/objtool/arch/x86/insn/insn.h b/tools/objtool/arch/x86/insn/insn.h
deleted file mode 100644
index e23578c7b1be..000000000000
--- a/tools/objtool/arch/x86/insn/insn.h
+++ /dev/null
@@ -1,211 +0,0 @@
-#ifndef _ASM_X86_INSN_H
-#define _ASM_X86_INSN_H
-/*
- * x86 instruction analysis
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2009
- */
-
-/* insn_attr_t is defined in inat.h */
-#include "inat.h"
-
-struct insn_field {
-	union {
-		insn_value_t value;
-		insn_byte_t bytes[4];
-	};
-	/* !0 if we've run insn_get_xxx() for this field */
-	unsigned char got;
-	unsigned char nbytes;
-};
-
-struct insn {
-	struct insn_field prefixes;	/*
-					 * Prefixes
-					 * prefixes.bytes[3]: last prefix
-					 */
-	struct insn_field rex_prefix;	/* REX prefix */
-	struct insn_field vex_prefix;	/* VEX prefix */
-	struct insn_field opcode;	/*
-					 * opcode.bytes[0]: opcode1
-					 * opcode.bytes[1]: opcode2
-					 * opcode.bytes[2]: opcode3
-					 */
-	struct insn_field modrm;
-	struct insn_field sib;
-	struct insn_field displacement;
-	union {
-		struct insn_field immediate;
-		struct insn_field moffset1;	/* for 64bit MOV */
-		struct insn_field immediate1;	/* for 64bit imm or off16/32 */
-	};
-	union {
-		struct insn_field moffset2;	/* for 64bit MOV */
-		struct insn_field immediate2;	/* for 64bit imm or seg16 */
-	};
-
-	insn_attr_t attr;
-	unsigned char opnd_bytes;
-	unsigned char addr_bytes;
-	unsigned char length;
-	unsigned char x86_64;
-
-	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
-	const insn_byte_t *end_kaddr;	/* kernel address of last insn in buffer */
-	const insn_byte_t *next_byte;
-};
-
-#define MAX_INSN_SIZE	15
-
-#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
-#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
-#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
-
-#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
-#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
-#define X86_SIB_BASE(sib) ((sib) & 0x07)
-
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
-
-/* VEX bit flags  */
-#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
-#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
-#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
-#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
-#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
-/* VEX bit fields */
-#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
-#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
-#define X86_VEX2_M	1			/* VEX2.M always 1 */
-#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
-#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
-#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
-
-extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
-
-/* Attribute will be determined after getting ModRM (for opcode groups) */
-static inline void insn_get_attribute(struct insn *insn)
-{
-	insn_get_modrm(insn);
-}
-
-/* Instruction uses RIP-relative addressing */
-extern int insn_rip_relative(struct insn *insn);
-
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
-				    const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
-	insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
-	insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
-static inline int insn_is_avx(struct insn *insn)
-{
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-	return (insn->vex_prefix.value != 0);
-}
-
-static inline int insn_is_evex(struct insn *insn)
-{
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-	return (insn->vex_prefix.nbytes == 4);
-}
-
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
-	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
-		insn->displacement.got && insn->immediate.got;
-}
-
-static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
-{
-	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
-		return X86_VEX2_M;
-	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
-		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
-	else					/* EVEX */
-		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
-}
-
-static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
-{
-	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
-		return X86_VEX_P(insn->vex_prefix.bytes[1]);
-	else
-		return X86_VEX_P(insn->vex_prefix.bytes[2]);
-}
-
-/* Get the last prefix id from last prefix or VEX prefix */
-static inline int insn_last_prefix_id(struct insn *insn)
-{
-	if (insn_is_avx(insn))
-		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
-
-	if (insn->prefixes.bytes[3])
-		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
-
-	return 0;
-}
-
-/* Offset of each field from kaddr */
-static inline int insn_offset_rex_prefix(struct insn *insn)
-{
-	return insn->prefixes.nbytes;
-}
-static inline int insn_offset_vex_prefix(struct insn *insn)
-{
-	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
-}
-static inline int insn_offset_opcode(struct insn *insn)
-{
-	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
-}
-static inline int insn_offset_modrm(struct insn *insn)
-{
-	return insn_offset_opcode(insn) + insn->opcode.nbytes;
-}
-static inline int insn_offset_sib(struct insn *insn)
-{
-	return insn_offset_modrm(insn) + insn->modrm.nbytes;
-}
-static inline int insn_offset_displacement(struct insn *insn)
-{
-	return insn_offset_sib(insn) + insn->sib.nbytes;
-}
-static inline int insn_offset_immediate(struct insn *insn)
-{
-	return insn_offset_displacement(insn) + insn->displacement.nbytes;
-}
-
-#endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
deleted file mode 100644
index 12e377184ee4..000000000000
--- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt
+++ /dev/null
@@ -1,1063 +0,0 @@
-# x86 Opcode Maps
-#
-# This is (mostly) based on following documentations.
-# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
-#   (#326018-047US, June 2013)
-#
-#<Opcode maps>
-# Table: table-name
-# Referrer: escaped-name
-# AVXcode: avx-code
-# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
-# (or)
-# opcode: escape # escaped-name
-# EndTable
-#
-# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
-# mnemonics that begin with lowercase 'k' accept a VEX prefix
-#
-#<group maps>
-# GrpTable: GrpXXX
-# reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
-# EndTable
-#
-# AVX Superscripts
-#  (ev): this opcode requires EVEX prefix.
-#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
-#  (v): this opcode requires VEX prefix.
-#  (v1): this opcode only supports 128bit VEX.
-#
-# Last Prefix Superscripts
-#  - (66): the last prefix is 0x66
-#  - (F3): the last prefix is 0xF3
-#  - (F2): the last prefix is 0xF2
-#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
-#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
-
-Table: one byte opcode
-Referrer:
-AVXcode:
-# 0x00 - 0x0f
-00: ADD Eb,Gb
-01: ADD Ev,Gv
-02: ADD Gb,Eb
-03: ADD Gv,Ev
-04: ADD AL,Ib
-05: ADD rAX,Iz
-06: PUSH ES (i64)
-07: POP ES (i64)
-08: OR Eb,Gb
-09: OR Ev,Gv
-0a: OR Gb,Eb
-0b: OR Gv,Ev
-0c: OR AL,Ib
-0d: OR rAX,Iz
-0e: PUSH CS (i64)
-0f: escape # 2-byte escape
-# 0x10 - 0x1f
-10: ADC Eb,Gb
-11: ADC Ev,Gv
-12: ADC Gb,Eb
-13: ADC Gv,Ev
-14: ADC AL,Ib
-15: ADC rAX,Iz
-16: PUSH SS (i64)
-17: POP SS (i64)
-18: SBB Eb,Gb
-19: SBB Ev,Gv
-1a: SBB Gb,Eb
-1b: SBB Gv,Ev
-1c: SBB AL,Ib
-1d: SBB rAX,Iz
-1e: PUSH DS (i64)
-1f: POP DS (i64)
-# 0x20 - 0x2f
-20: AND Eb,Gb
-21: AND Ev,Gv
-22: AND Gb,Eb
-23: AND Gv,Ev
-24: AND AL,Ib
-25: AND rAx,Iz
-26: SEG=ES (Prefix)
-27: DAA (i64)
-28: SUB Eb,Gb
-29: SUB Ev,Gv
-2a: SUB Gb,Eb
-2b: SUB Gv,Ev
-2c: SUB AL,Ib
-2d: SUB rAX,Iz
-2e: SEG=CS (Prefix)
-2f: DAS (i64)
-# 0x30 - 0x3f
-30: XOR Eb,Gb
-31: XOR Ev,Gv
-32: XOR Gb,Eb
-33: XOR Gv,Ev
-34: XOR AL,Ib
-35: XOR rAX,Iz
-36: SEG=SS (Prefix)
-37: AAA (i64)
-38: CMP Eb,Gb
-39: CMP Ev,Gv
-3a: CMP Gb,Eb
-3b: CMP Gv,Ev
-3c: CMP AL,Ib
-3d: CMP rAX,Iz
-3e: SEG=DS (Prefix)
-3f: AAS (i64)
-# 0x40 - 0x4f
-40: INC eAX (i64) | REX (o64)
-41: INC eCX (i64) | REX.B (o64)
-42: INC eDX (i64) | REX.X (o64)
-43: INC eBX (i64) | REX.XB (o64)
-44: INC eSP (i64) | REX.R (o64)
-45: INC eBP (i64) | REX.RB (o64)
-46: INC eSI (i64) | REX.RX (o64)
-47: INC eDI (i64) | REX.RXB (o64)
-48: DEC eAX (i64) | REX.W (o64)
-49: DEC eCX (i64) | REX.WB (o64)
-4a: DEC eDX (i64) | REX.WX (o64)
-4b: DEC eBX (i64) | REX.WXB (o64)
-4c: DEC eSP (i64) | REX.WR (o64)
-4d: DEC eBP (i64) | REX.WRB (o64)
-4e: DEC eSI (i64) | REX.WRX (o64)
-4f: DEC eDI (i64) | REX.WRXB (o64)
-# 0x50 - 0x5f
-50: PUSH rAX/r8 (d64)
-51: PUSH rCX/r9 (d64)
-52: PUSH rDX/r10 (d64)
-53: PUSH rBX/r11 (d64)
-54: PUSH rSP/r12 (d64)
-55: PUSH rBP/r13 (d64)
-56: PUSH rSI/r14 (d64)
-57: PUSH rDI/r15 (d64)
-58: POP rAX/r8 (d64)
-59: POP rCX/r9 (d64)
-5a: POP rDX/r10 (d64)
-5b: POP rBX/r11 (d64)
-5c: POP rSP/r12 (d64)
-5d: POP rBP/r13 (d64)
-5e: POP rSI/r14 (d64)
-5f: POP rDI/r15 (d64)
-# 0x60 - 0x6f
-60: PUSHA/PUSHAD (i64)
-61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
-63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
-64: SEG=FS (Prefix)
-65: SEG=GS (Prefix)
-66: Operand-Size (Prefix)
-67: Address-Size (Prefix)
-68: PUSH Iz (d64)
-69: IMUL Gv,Ev,Iz
-6a: PUSH Ib (d64)
-6b: IMUL Gv,Ev,Ib
-6c: INS/INSB Yb,DX
-6d: INS/INSW/INSD Yz,DX
-6e: OUTS/OUTSB DX,Xb
-6f: OUTS/OUTSW/OUTSD DX,Xz
-# 0x70 - 0x7f
-70: JO Jb
-71: JNO Jb
-72: JB/JNAE/JC Jb
-73: JNB/JAE/JNC Jb
-74: JZ/JE Jb
-75: JNZ/JNE Jb
-76: JBE/JNA Jb
-77: JNBE/JA Jb
-78: JS Jb
-79: JNS Jb
-7a: JP/JPE Jb
-7b: JNP/JPO Jb
-7c: JL/JNGE Jb
-7d: JNL/JGE Jb
-7e: JLE/JNG Jb
-7f: JNLE/JG Jb
-# 0x80 - 0x8f
-80: Grp1 Eb,Ib (1A)
-81: Grp1 Ev,Iz (1A)
-82: Grp1 Eb,Ib (1A),(i64)
-83: Grp1 Ev,Ib (1A)
-84: TEST Eb,Gb
-85: TEST Ev,Gv
-86: XCHG Eb,Gb
-87: XCHG Ev,Gv
-88: MOV Eb,Gb
-89: MOV Ev,Gv
-8a: MOV Gb,Eb
-8b: MOV Gv,Ev
-8c: MOV Ev,Sw
-8d: LEA Gv,M
-8e: MOV Sw,Ew
-8f: Grp1A (1A) | POP Ev (d64)
-# 0x90 - 0x9f
-90: NOP | PAUSE (F3) | XCHG r8,rAX
-91: XCHG rCX/r9,rAX
-92: XCHG rDX/r10,rAX
-93: XCHG rBX/r11,rAX
-94: XCHG rSP/r12,rAX
-95: XCHG rBP/r13,rAX
-96: XCHG rSI/r14,rAX
-97: XCHG rDI/r15,rAX
-98: CBW/CWDE/CDQE
-99: CWD/CDQ/CQO
-9a: CALLF Ap (i64)
-9b: FWAIT/WAIT
-9c: PUSHF/D/Q Fv (d64)
-9d: POPF/D/Q Fv (d64)
-9e: SAHF
-9f: LAHF
-# 0xa0 - 0xaf
-a0: MOV AL,Ob
-a1: MOV rAX,Ov
-a2: MOV Ob,AL
-a3: MOV Ov,rAX
-a4: MOVS/B Yb,Xb
-a5: MOVS/W/D/Q Yv,Xv
-a6: CMPS/B Xb,Yb
-a7: CMPS/W/D Xv,Yv
-a8: TEST AL,Ib
-a9: TEST rAX,Iz
-aa: STOS/B Yb,AL
-ab: STOS/W/D/Q Yv,rAX
-ac: LODS/B AL,Xb
-ad: LODS/W/D/Q rAX,Xv
-ae: SCAS/B AL,Yb
-# Note: The May 2011 Intel manual shows Xv for the second parameter of the
-# next instruction but Yv is correct
-af: SCAS/W/D/Q rAX,Yv
-# 0xb0 - 0xbf
-b0: MOV AL/R8L,Ib
-b1: MOV CL/R9L,Ib
-b2: MOV DL/R10L,Ib
-b3: MOV BL/R11L,Ib
-b4: MOV AH/R12L,Ib
-b5: MOV CH/R13L,Ib
-b6: MOV DH/R14L,Ib
-b7: MOV BH/R15L,Ib
-b8: MOV rAX/r8,Iv
-b9: MOV rCX/r9,Iv
-ba: MOV rDX/r10,Iv
-bb: MOV rBX/r11,Iv
-bc: MOV rSP/r12,Iv
-bd: MOV rBP/r13,Iv
-be: MOV rSI/r14,Iv
-bf: MOV rDI/r15,Iv
-# 0xc0 - 0xcf
-c0: Grp2 Eb,Ib (1A)
-c1: Grp2 Ev,Ib (1A)
-c2: RETN Iw (f64)
-c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
-c6: Grp11A Eb,Ib (1A)
-c7: Grp11B Ev,Iz (1A)
-c8: ENTER Iw,Ib
-c9: LEAVE (d64)
-ca: RETF Iw
-cb: RETF
-cc: INT3
-cd: INT Ib
-ce: INTO (i64)
-cf: IRET/D/Q
-# 0xd0 - 0xdf
-d0: Grp2 Eb,1 (1A)
-d1: Grp2 Ev,1 (1A)
-d2: Grp2 Eb,CL (1A)
-d3: Grp2 Ev,CL (1A)
-d4: AAM Ib (i64)
-d5: AAD Ib (i64)
-d6:
-d7: XLAT/XLATB
-d8: ESC
-d9: ESC
-da: ESC
-db: ESC
-dc: ESC
-dd: ESC
-de: ESC
-df: ESC
-# 0xe0 - 0xef
-# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
-# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
-# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64)
-e1: LOOPE/LOOPZ Jb (f64)
-e2: LOOP Jb (f64)
-e3: JrCXZ Jb (f64)
-e4: IN AL,Ib
-e5: IN eAX,Ib
-e6: OUT Ib,AL
-e7: OUT Ib,eAX
-# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
-# in "near" jumps and calls is 16-bit. For CALL,
-# push of return address is 16-bit wide, RSP is decremented by 2
-# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64)
-e9: JMP-near Jz (f64)
-ea: JMP-far Ap (i64)
-eb: JMP-short Jb (f64)
-ec: IN AL,DX
-ed: IN eAX,DX
-ee: OUT DX,AL
-ef: OUT DX,eAX
-# 0xf0 - 0xff
-f0: LOCK (Prefix)
-f1:
-f2: REPNE (Prefix) | XACQUIRE (Prefix)
-f3: REP/REPE (Prefix) | XRELEASE (Prefix)
-f4: HLT
-f5: CMC
-f6: Grp3_1 Eb (1A)
-f7: Grp3_2 Ev (1A)
-f8: CLC
-f9: STC
-fa: CLI
-fb: STI
-fc: CLD
-fd: STD
-fe: Grp4 (1A)
-ff: Grp5 (1A)
-EndTable
-
-Table: 2-byte opcode (0x0f)
-Referrer: 2-byte escape
-AVXcode: 1
-# 0x0f 0x00-0x0f
-00: Grp6 (1A)
-01: Grp7 (1A)
-02: LAR Gv,Ew
-03: LSL Gv,Ew
-04:
-05: SYSCALL (o64)
-06: CLTS
-07: SYSRET (o64)
-08: INVD
-09: WBINVD
-0a:
-0b: UD2 (1B)
-0c:
-# AMD's prefetch group. Intel supports prefetchw(/1) only.
-0d: GrpP
-0e: FEMMS
-# 3DNow! uses the last imm byte as opcode extension.
-0f: 3DNow! Pq,Qq,Ib
-# 0x0f 0x10-0x1f
-# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
-# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
-# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
-# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
-# Reference A.1
-10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
-11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
-12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
-13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
-14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
-15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
-16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
-17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
-18: Grp16 (1A)
-19:
-# Intel SDM opcode map does not list MPX instructions. For now using Gv for
-# bnd registers and Ev for everything else is OK because the instruction
-# decoder does not use the information except as an indication that there is
-# a ModR/M byte.
-1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
-1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
-1c:
-1d:
-1e:
-1f: NOP Ev
-# 0x0f 0x20-0x2f
-20: MOV Rd,Cd
-21: MOV Rd,Dd
-22: MOV Cd,Rd
-23: MOV Dd,Rd
-24:
-25:
-26:
-27:
-28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
-29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
-2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
-2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
-2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
-2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
-2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
-2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
-# 0x0f 0x30-0x3f
-30: WRMSR
-31: RDTSC
-32: RDMSR
-33: RDPMC
-34: SYSENTER
-35: SYSEXIT
-36:
-37: GETSEC
-38: escape # 3-byte escape 1
-39:
-3a: escape # 3-byte escape 2
-3b:
-3c:
-3d:
-3e:
-3f:
-# 0x0f 0x40-0x4f
-40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
-42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
-43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
-45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
-46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
-47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
-48: CMOVS Gv,Ev
-49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
-4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
-4c: CMOVL/NGE Gv,Ev
-4d: CMOVNL/GE Gv,Ev
-4e: CMOVLE/NG Gv,Ev
-4f: CMOVNLE/G Gv,Ev
-# 0x0f 0x50-0x5f
-50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
-51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
-52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
-53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
-54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
-55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
-56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
-57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
-58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
-59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
-5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
-5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
-5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
-5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
-5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
-# 0x0f 0x60-0x6f
-60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
-61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
-62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
-63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
-64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
-65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
-66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
-67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
-68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
-69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
-6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
-6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
-6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
-6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
-6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
-# 0x0f 0x70-0x7f
-70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
-71: Grp12 (1A)
-72: Grp13 (1A)
-73: Grp14 (1A)
-74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
-75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
-76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
-# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
-77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
-79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
-7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
-7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
-7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
-7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
-7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
-# 0x0f 0x80-0x8f
-# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64)
-81: JNO Jz (f64)
-82: JB/JC/JNAE Jz (f64)
-83: JAE/JNB/JNC Jz (f64)
-84: JE/JZ Jz (f64)
-85: JNE/JNZ Jz (f64)
-86: JBE/JNA Jz (f64)
-87: JA/JNBE Jz (f64)
-88: JS Jz (f64)
-89: JNS Jz (f64)
-8a: JP/JPE Jz (f64)
-8b: JNP/JPO Jz (f64)
-8c: JL/JNGE Jz (f64)
-8d: JNL/JGE Jz (f64)
-8e: JLE/JNG Jz (f64)
-8f: JNLE/JG Jz (f64)
-# 0x0f 0x90-0x9f
-90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
-91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
-92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
-93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
-94: SETE/Z Eb
-95: SETNE/NZ Eb
-96: SETBE/NA Eb
-97: SETA/NBE Eb
-98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
-99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
-9a: SETP/PE Eb
-9b: SETNP/PO Eb
-9c: SETL/NGE Eb
-9d: SETNL/GE Eb
-9e: SETLE/NG Eb
-9f: SETNLE/G Eb
-# 0x0f 0xa0-0xaf
-a0: PUSH FS (d64)
-a1: POP FS (d64)
-a2: CPUID
-a3: BT Ev,Gv
-a4: SHLD Ev,Gv,Ib
-a5: SHLD Ev,Gv,CL
-a6: GrpPDLK
-a7: GrpRNG
-a8: PUSH GS (d64)
-a9: POP GS (d64)
-aa: RSM
-ab: BTS Ev,Gv
-ac: SHRD Ev,Gv,Ib
-ad: SHRD Ev,Gv,CL
-ae: Grp15 (1A),(1C)
-af: IMUL Gv,Ev
-# 0x0f 0xb0-0xbf
-b0: CMPXCHG Eb,Gb
-b1: CMPXCHG Ev,Gv
-b2: LSS Gv,Mp
-b3: BTR Ev,Gv
-b4: LFS Gv,Mp
-b5: LGS Gv,Mp
-b6: MOVZX Gv,Eb
-b7: MOVZX Gv,Ew
-b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
-b9: Grp10 (1A)
-ba: Grp8 Ev,Ib (1A)
-bb: BTC Ev,Gv
-bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
-be: MOVSX Gv,Eb
-bf: MOVSX Gv,Ew
-# 0x0f 0xc0-0xcf
-c0: XADD Eb,Gb
-c1: XADD Ev,Gv
-c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
-c3: movnti My,Gy
-c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
-c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
-c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
-c7: Grp9 (1A)
-c8: BSWAP RAX/EAX/R8/R8D
-c9: BSWAP RCX/ECX/R9/R9D
-ca: BSWAP RDX/EDX/R10/R10D
-cb: BSWAP RBX/EBX/R11/R11D
-cc: BSWAP RSP/ESP/R12/R12D
-cd: BSWAP RBP/EBP/R13/R13D
-ce: BSWAP RSI/ESI/R14/R14D
-cf: BSWAP RDI/EDI/R15/R15D
-# 0x0f 0xd0-0xdf
-d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
-d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
-d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
-d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
-d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
-d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
-d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
-d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
-d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
-d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
-da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
-dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
-dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
-de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0xe0-0xef
-e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
-e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
-e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
-e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
-e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
-e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
-e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
-e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
-e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
-ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
-ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
-ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
-ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0xf0-0xff
-f0: vlddqu Vx,Mx (F2)
-f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
-f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
-f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
-f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
-f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
-f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
-f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
-f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
-f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
-fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
-fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
-fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
-fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
-fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
-EndTable
-
-Table: 3-byte opcode 1 (0x0f 0x38)
-Referrer: 3-byte escape 1
-AVXcode: 2
-# 0x0f 0x38 0x00-0x0f
-00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
-01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
-02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
-03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
-04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
-05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
-06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
-07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
-08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
-09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
-0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
-0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
-0c: vpermilps Vx,Hx,Wx (66),(v)
-0d: vpermilpd Vx,Hx,Wx (66),(v)
-0e: vtestps Vx,Wx (66),(v)
-0f: vtestpd Vx,Wx (66),(v)
-# 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
-11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
-12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
-13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
-14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
-15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
-16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
-17: vptest Vx,Wx (66)
-18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
-1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
-1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
-1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
-1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
-1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f: vpabsq Vx,Wx (66),(ev)
-# 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
-21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
-24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
-26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
-27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
-28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
-2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
-2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
-2e: vmaskmovps Mx,Hx,Vx (66),(v)
-2f: vmaskmovpd Mx,Hx,Vx (66),(v)
-# 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
-31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
-34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
-36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
-37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
-39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
-3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
-3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
-3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
-3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
-41: vphminposuw Vdq,Wdq (66),(v1)
-42: vgetexpps/d Vx,Wx (66),(ev)
-43: vgetexpss/d Vx,Hx,Wx (66),(ev)
-44: vplzcntd/q Vx,Wx (66),(ev)
-45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
-47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x4b
-4c: vrcp14ps/d Vpd,Wpd (66),(ev)
-4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
-4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
-4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-# Skip 0x50-0x57
-58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
-5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
-5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-# Skip 0x5c-0x63
-64: vpblendmd/q Vx,Hx,Wx (66),(ev)
-65: vblendmps/d Vx,Hx,Wx (66),(ev)
-66: vpblendmb/w Vx,Hx,Wx (66),(ev)
-# Skip 0x67-0x74
-75: vpermi2b/w Vx,Hx,Wx (66),(ev)
-76: vpermi2d/q Vx,Hx,Wx (66),(ev)
-77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
-78: vpbroadcastb Vx,Wx (66),(v)
-79: vpbroadcastw Vx,Wx (66),(v)
-7a: vpbroadcastb Vx,Rv (66),(ev)
-7b: vpbroadcastw Vx,Rv (66),(ev)
-7c: vpbroadcastd/q Vx,Rv (66),(ev)
-7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
-7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
-7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
-80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
-82: INVPCID Gy,Mdq (66)
-83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
-88: vexpandps/d Vpd,Wpd (66),(ev)
-89: vpexpandd/q Vx,Wx (66),(ev)
-8a: vcompressps/d Wx,Vx (66),(ev)
-8b: vpcompressd/q Wx,Vx (66),(ev)
-8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
-8d: vpermb/w Vx,Hx,Wx (66),(ev)
-8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
-# 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
-91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
-92: vgatherdps/d Vx,Hx,Wx (66),(v)
-93: vgatherqps/d Vx,Hx,Wx (66),(v)
-94:
-95:
-96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
-97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
-98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
-99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
-9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
-9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
-9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-a0: vpscatterdd/q Wx,Vx (66),(ev)
-a1: vpscatterqd/q Wx,Vx (66),(ev)
-a2: vscatterdps/d Wx,Vx (66),(ev)
-a3: vscatterqps/d Wx,Vx (66),(ev)
-a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
-a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
-a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
-a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
-ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
-ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
-af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
-b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
-b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
-b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
-b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
-b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
-ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
-bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
-bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
-bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
-be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
-bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
-# 0x0f 0x38 0xc0-0xff
-c4: vpconflictd/q Vx,Wx (66),(ev)
-c6: Grp18 (1A)
-c7: Grp19 (1A)
-c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
-c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
-cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
-cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
-cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
-db: VAESIMC Vdq,Wdq (66),(v1)
-dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
-dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
-de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
-df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
-f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
-f2: ANDN Gy,By,Ey (v)
-f3: Grp17 (1A)
-f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
-f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
-EndTable
-
-Table: 3-byte opcode 2 (0x0f 0x3a)
-Referrer: 3-byte escape 2
-AVXcode: 3
-# 0x0f 0x3a 0x00-0xff
-00: vpermq Vqq,Wqq,Ib (66),(v)
-01: vpermpd Vqq,Wqq,Ib (66),(v)
-02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
-04: vpermilps Vx,Wx,Ib (66),(v)
-05: vpermilpd Vx,Wx,Ib (66),(v)
-06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
-07:
-08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
-09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
-0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
-0c: vblendps Vx,Hx,Wx,Ib (66)
-0d: vblendpd Vx,Hx,Wx,Ib (66)
-0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
-0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
-14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
-15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
-16: vpextrd/q Ey,Vdq,Ib (66),(v1)
-17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
-19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
-1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
-1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
-1d: vcvtps2ph Wx,Vx,Ib (66),(v)
-1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
-1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
-20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
-21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
-22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
-26: vgetmantps/d Vx,Wx,Ib (66),(ev)
-27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
-30: kshiftrb/w Vk,Uk,Ib (66),(v)
-31: kshiftrd/q Vk,Uk,Ib (66),(v)
-32: kshiftlb/w Vk,Uk,Ib (66),(v)
-33: kshiftld/q Vk,Uk,Ib (66),(v)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
-39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
-3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
-3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
-3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
-3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
-40: vdpps Vx,Hx,Wx,Ib (66)
-41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
-43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
-46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
-4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
-4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
-4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
-50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
-51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
-54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
-55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
-56: vreduceps/d Vx,Wx,Ib (66),(ev)
-57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
-60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
-61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
-62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
-63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
-66: vfpclassps/d Vk,Wx,Ib (66),(ev)
-67: vfpclassss/d Vk,Wx,Ib (66),(ev)
-cc: sha1rnds4 Vdq,Wdq,Ib
-df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
-f0: RORX Gy,Ey,Ib (F2),(v)
-EndTable
-
-GrpTable: Grp1
-0: ADD
-1: OR
-2: ADC
-3: SBB
-4: AND
-5: SUB
-6: XOR
-7: CMP
-EndTable
-
-GrpTable: Grp1A
-0: POP
-EndTable
-
-GrpTable: Grp2
-0: ROL
-1: ROR
-2: RCL
-3: RCR
-4: SHL/SAL
-5: SHR
-6:
-7: SAR
-EndTable
-
-GrpTable: Grp3_1
-0: TEST Eb,Ib
-1:
-2: NOT Eb
-3: NEG Eb
-4: MUL AL,Eb
-5: IMUL AL,Eb
-6: DIV AL,Eb
-7: IDIV AL,Eb
-EndTable
-
-GrpTable: Grp3_2
-0: TEST Ev,Iz
-1:
-2: NOT Ev
-3: NEG Ev
-4: MUL rAX,Ev
-5: IMUL rAX,Ev
-6: DIV rAX,Ev
-7: IDIV rAX,Ev
-EndTable
-
-GrpTable: Grp4
-0: INC Eb
-1: DEC Eb
-EndTable
-
-GrpTable: Grp5
-0: INC Ev
-1: DEC Ev
-# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-2: CALLN Ev (f64)
-3: CALLF Ep
-4: JMPN Ev (f64)
-5: JMPF Mp
-6: PUSH Ev (d64)
-7:
-EndTable
-
-GrpTable: Grp6
-0: SLDT Rv/Mw
-1: STR Rv/Mw
-2: LLDT Ew
-3: LTR Ew
-4: VERR Ew
-5: VERW Ew
-EndTable
-
-GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
-3: LIDT Ms
-4: SMSW Mw/Rv
-5: rdpkru (110),(11B) | wrpkru (111),(11B)
-6: LMSW Ew
-7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
-EndTable
-
-GrpTable: Grp8
-4: BT
-5: BTS
-6: BTR
-7: BTC
-EndTable
-
-GrpTable: Grp9
-1: CMPXCHG8B/16B Mq/Mdq
-3: xrstors
-4: xsavec
-5: xsaves
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
-EndTable
-
-GrpTable: Grp10
-EndTable
-
-# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
-GrpTable: Grp11A
-0: MOV Eb,Ib
-7: XABORT Ib (000),(11B)
-EndTable
-
-GrpTable: Grp11B
-0: MOV Eb,Iz
-7: XBEGIN Jz (000),(11B)
-EndTable
-
-GrpTable: Grp12
-2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
-4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
-6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp13
-0: vprord/q Hx,Wx,Ib (66),(ev)
-1: vprold/q Hx,Wx,Ib (66),(ev)
-2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
-6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp14
-2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
-3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
-6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
-7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp15
-0: fxsave | RDFSBASE Ry (F3),(11B)
-1: fxstor | RDGSBASE Ry (F3),(11B)
-2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
-3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
-4: XSAVE | ptwrite Ey (F3),(11B)
-5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B)
-7: clflush | clflushopt (66) | sfence (11B)
-EndTable
-
-GrpTable: Grp16
-0: prefetch NTA
-1: prefetch T0
-2: prefetch T1
-3: prefetch T2
-EndTable
-
-GrpTable: Grp17
-1: BLSR By,Ey (v)
-2: BLSMSK By,Ey (v)
-3: BLSI By,Ey (v)
-EndTable
-
-GrpTable: Grp18
-1: vgatherpf0dps/d Wx (66),(ev)
-2: vgatherpf1dps/d Wx (66),(ev)
-5: vscatterpf0dps/d Wx (66),(ev)
-6: vscatterpf1dps/d Wx (66),(ev)
-EndTable
-
-GrpTable: Grp19
-1: vgatherpf0qps/d Wx (66),(ev)
-2: vgatherpf1qps/d Wx (66),(ev)
-5: vscatterpf0qps/d Wx (66),(ev)
-6: vscatterpf1qps/d Wx (66),(ev)
-EndTable
-
-# AMD's Prefetch Group
-GrpTable: GrpP
-0: PREFETCH
-1: PREFETCHW
-EndTable
-
-GrpTable: GrpPDLK
-0: MONTMUL
-1: XSHA1
-2: XSHA2
-EndTable
-
-GrpTable: GrpRNG
-0: xstore-rng
-1: xcrypt-ecb
-2: xcrypt-cbc
-4: xcrypt-cfb
-5: xcrypt-ofb
-EndTable
diff --git a/tools/objtool/arch/x86/lib/inat.c b/tools/objtool/arch/x86/lib/inat.c
new file mode 100644
index 000000000000..c1f01a8e9f65
--- /dev/null
+++ b/tools/objtool/arch/x86/lib/inat.c
@@ -0,0 +1,97 @@
+/*
+ * x86 instruction attribute tables
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <asm/insn.h>
+
+/* Attribute tables are generated from opcode map */
+#include "inat-tables.c"
+
+/* Attribute search APIs */
+insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
+{
+	return inat_primary_table[opcode];
+}
+
+int inat_get_last_prefix_id(insn_byte_t last_pfx)
+{
+	insn_attr_t lpfx_attr;
+
+	lpfx_attr = inat_get_opcode_attribute(last_pfx);
+	return inat_last_prefix_id(lpfx_attr);
+}
+
+insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
+				      insn_attr_t esc_attr)
+{
+	const insn_attr_t *table;
+	int n;
+
+	n = inat_escape_id(esc_attr);
+
+	table = inat_escape_tables[n][0];
+	if (!table)
+		return 0;
+	if (inat_has_variant(table[opcode]) && lpfx_id) {
+		table = inat_escape_tables[n][lpfx_id];
+		if (!table)
+			return 0;
+	}
+	return table[opcode];
+}
+
+insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
+				     insn_attr_t grp_attr)
+{
+	const insn_attr_t *table;
+	int n;
+
+	n = inat_group_id(grp_attr);
+
+	table = inat_group_tables[n][0];
+	if (!table)
+		return inat_group_common_attribute(grp_attr);
+	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
+		table = inat_group_tables[n][lpfx_id];
+		if (!table)
+			return inat_group_common_attribute(grp_attr);
+	}
+	return table[X86_MODRM_REG(modrm)] |
+	       inat_group_common_attribute(grp_attr);
+}
+
+insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
+				   insn_byte_t vex_p)
+{
+	const insn_attr_t *table;
+	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
+		return 0;
+	/* At first, this checks the master table */
+	table = inat_avx_tables[vex_m][0];
+	if (!table)
+		return 0;
+	if (!inat_is_group(table[opcode]) && vex_p) {
+		/* If this is not a group, get attribute directly */
+		table = inat_avx_tables[vex_m][vex_p];
+		if (!table)
+			return 0;
+	}
+	return table[opcode];
+}
+
diff --git a/tools/objtool/arch/x86/lib/insn.c b/tools/objtool/arch/x86/lib/insn.c
new file mode 100644
index 000000000000..1088eb8f3a5f
--- /dev/null
+++ b/tools/objtool/arch/x86/lib/insn.c
@@ -0,0 +1,606 @@
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004, 2009
+ */
+
+#ifdef __KERNEL__
+#include <linux/string.h>
+#else
+#include <string.h>
+#endif
+#include <asm/inat.h>
+#include <asm/insn.h>
+
+/* Verify next sizeof(t) bytes can be on the same instruction */
+#define validate_next(t, insn, n)	\
+	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
+
+#define __get_next(t, insn)	\
+	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
+
+#define __peek_nbyte_next(t, insn, n)	\
+	({ t r = *(t*)((insn)->next_byte + n); r; })
+
+#define get_next(t, insn)	\
+	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
+
+#define peek_nbyte_next(t, insn, n)	\
+	({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); })
+
+#define peek_next(t, insn)	peek_nbyte_next(t, insn, 0)
+
+/**
+ * insn_init() - initialize struct insn
+ * @insn:	&struct insn to be initialized
+ * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
+ * @x86_64:	!0 for 64-bit kernel or 64-bit app
+ */
+void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
+{
+	/*
+	 * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid
+	 * even if the input buffer is long enough to hold them.
+	 */
+	if (buf_len > MAX_INSN_SIZE)
+		buf_len = MAX_INSN_SIZE;
+
+	memset(insn, 0, sizeof(*insn));
+	insn->kaddr = kaddr;
+	insn->end_kaddr = kaddr + buf_len;
+	insn->next_byte = kaddr;
+	insn->x86_64 = x86_64 ? 1 : 0;
+	insn->opnd_bytes = 4;
+	if (x86_64)
+		insn->addr_bytes = 8;
+	else
+		insn->addr_bytes = 4;
+}
+
+/**
+ * insn_get_prefixes - scan x86 instruction prefix bytes
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
+ * to point to the (first) opcode.  No effect if @insn->prefixes.got
+ * is already set.
+ */
+void insn_get_prefixes(struct insn *insn)
+{
+	struct insn_field *prefixes = &insn->prefixes;
+	insn_attr_t attr;
+	insn_byte_t b, lb;
+	int i, nb;
+
+	if (prefixes->got)
+		return;
+
+	nb = 0;
+	lb = 0;
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	while (inat_is_legacy_prefix(attr)) {
+		/* Skip if same prefix */
+		for (i = 0; i < nb; i++)
+			if (prefixes->bytes[i] == b)
+				goto found;
+		if (nb == 4)
+			/* Invalid instruction */
+			break;
+		prefixes->bytes[nb++] = b;
+		if (inat_is_address_size_prefix(attr)) {
+			/* address size switches 2/4 or 4/8 */
+			if (insn->x86_64)
+				insn->addr_bytes ^= 12;
+			else
+				insn->addr_bytes ^= 6;
+		} else if (inat_is_operand_size_prefix(attr)) {
+			/* oprand size switches 2/4 */
+			insn->opnd_bytes ^= 6;
+		}
+found:
+		prefixes->nbytes++;
+		insn->next_byte++;
+		lb = b;
+		b = peek_next(insn_byte_t, insn);
+		attr = inat_get_opcode_attribute(b);
+	}
+	/* Set the last prefix */
+	if (lb && lb != insn->prefixes.bytes[3]) {
+		if (unlikely(insn->prefixes.bytes[3])) {
+			/* Swap the last prefix */
+			b = insn->prefixes.bytes[3];
+			for (i = 0; i < nb; i++)
+				if (prefixes->bytes[i] == lb)
+					prefixes->bytes[i] = b;
+		}
+		insn->prefixes.bytes[3] = lb;
+	}
+
+	/* Decode REX prefix */
+	if (insn->x86_64) {
+		b = peek_next(insn_byte_t, insn);
+		attr = inat_get_opcode_attribute(b);
+		if (inat_is_rex_prefix(attr)) {
+			insn->rex_prefix.value = b;
+			insn->rex_prefix.nbytes = 1;
+			insn->next_byte++;
+			if (X86_REX_W(b))
+				/* REX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		}
+	}
+	insn->rex_prefix.got = 1;
+
+	/* Decode VEX prefix */
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	if (inat_is_vex_prefix(attr)) {
+		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
+		if (!insn->x86_64) {
+			/*
+			 * In 32-bits mode, if the [7:6] bits (mod bits of
+			 * ModRM) on the second byte are not 11b, it is
+			 * LDS or LES or BOUND.
+			 */
+			if (X86_MODRM_MOD(b2) != 3)
+				goto vex_end;
+		}
+		insn->vex_prefix.bytes[0] = b;
+		insn->vex_prefix.bytes[1] = b2;
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else if (inat_is_vex3_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			insn->vex_prefix.nbytes = 3;
+			insn->next_byte += 3;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else {
+			/*
+			 * For VEX2, fake VEX3-like byte#2.
+			 * Makes it easier to decode vex.W, vex.vvvv,
+			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
+			 */
+			insn->vex_prefix.bytes[2] = b2 & 0x7f;
+			insn->vex_prefix.nbytes = 2;
+			insn->next_byte += 2;
+		}
+	}
+vex_end:
+	insn->vex_prefix.got = 1;
+
+	prefixes->got = 1;
+
+err_out:
+	return;
+}
+
+/**
+ * insn_get_opcode - collect opcode(s)
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates @insn->opcode, updates @insn->next_byte to point past the
+ * opcode byte(s), and set @insn->attr (except for groups).
+ * If necessary, first collects any preceding (prefix) bytes.
+ * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
+ * is already 1.
+ */
+void insn_get_opcode(struct insn *insn)
+{
+	struct insn_field *opcode = &insn->opcode;
+	insn_byte_t op;
+	int pfx_id;
+	if (opcode->got)
+		return;
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+
+	/* Get first opcode */
+	op = get_next(insn_byte_t, insn);
+	opcode->bytes[0] = op;
+	opcode->nbytes = 1;
+
+	/* Check if there is VEX prefix or not */
+	if (insn_is_avx(insn)) {
+		insn_byte_t m, p;
+		m = insn_vex_m_bits(insn);
+		p = insn_vex_p_bits(insn);
+		insn->attr = inat_get_avx_attribute(op, m, p);
+		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+		    (!inat_accept_vex(insn->attr) &&
+		     !inat_is_group(insn->attr)))
+			insn->attr = 0;	/* This instruction is bad */
+		goto end;	/* VEX has only 1 byte for opcode */
+	}
+
+	insn->attr = inat_get_opcode_attribute(op);
+	while (inat_is_escape(insn->attr)) {
+		/* Get escaped opcode */
+		op = get_next(insn_byte_t, insn);
+		opcode->bytes[opcode->nbytes++] = op;
+		pfx_id = insn_last_prefix_id(insn);
+		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
+	}
+	if (inat_must_vex(insn->attr))
+		insn->attr = 0;	/* This instruction is bad */
+end:
+	opcode->got = 1;
+
+err_out:
+	return;
+}
+
+/**
+ * insn_get_modrm - collect ModRM byte, if any
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates @insn->modrm and updates @insn->next_byte to point past the
+ * ModRM byte, if any.  If necessary, first collects the preceding bytes
+ * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
+ */
+void insn_get_modrm(struct insn *insn)
+{
+	struct insn_field *modrm = &insn->modrm;
+	insn_byte_t pfx_id, mod;
+	if (modrm->got)
+		return;
+	if (!insn->opcode.got)
+		insn_get_opcode(insn);
+
+	if (inat_has_modrm(insn->attr)) {
+		mod = get_next(insn_byte_t, insn);
+		modrm->value = mod;
+		modrm->nbytes = 1;
+		if (inat_is_group(insn->attr)) {
+			pfx_id = insn_last_prefix_id(insn);
+			insn->attr = inat_get_group_attribute(mod, pfx_id,
+							      insn->attr);
+			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
+				insn->attr = 0;	/* This is bad */
+		}
+	}
+
+	if (insn->x86_64 && inat_is_force64(insn->attr))
+		insn->opnd_bytes = 8;
+	modrm->got = 1;
+
+err_out:
+	return;
+}
+
+
+/**
+ * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.  No effect if @insn->x86_64 is 0.
+ */
+int insn_rip_relative(struct insn *insn)
+{
+	struct insn_field *modrm = &insn->modrm;
+
+	if (!insn->x86_64)
+		return 0;
+	if (!modrm->got)
+		insn_get_modrm(insn);
+	/*
+	 * For rip-relative instructions, the mod field (top 2 bits)
+	 * is zero and the r/m field (bottom 3 bits) is 0x5.
+	 */
+	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
+}
+
+/**
+ * insn_get_sib() - Get the SIB byte of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.
+ */
+void insn_get_sib(struct insn *insn)
+{
+	insn_byte_t modrm;
+
+	if (insn->sib.got)
+		return;
+	if (!insn->modrm.got)
+		insn_get_modrm(insn);
+	if (insn->modrm.nbytes) {
+		modrm = (insn_byte_t)insn->modrm.value;
+		if (insn->addr_bytes != 2 &&
+		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
+			insn->sib.value = get_next(insn_byte_t, insn);
+			insn->sib.nbytes = 1;
+		}
+	}
+	insn->sib.got = 1;
+
+err_out:
+	return;
+}
+
+
+/**
+ * insn_get_displacement() - Get the displacement of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * SIB byte.
+ * Displacement value is sign-expanded.
+ */
+void insn_get_displacement(struct insn *insn)
+{
+	insn_byte_t mod, rm, base;
+
+	if (insn->displacement.got)
+		return;
+	if (!insn->sib.got)
+		insn_get_sib(insn);
+	if (insn->modrm.nbytes) {
+		/*
+		 * Interpreting the modrm byte:
+		 * mod = 00 - no displacement fields (exceptions below)
+		 * mod = 01 - 1-byte displacement field
+		 * mod = 10 - displacement field is 4 bytes, or 2 bytes if
+		 * 	address size = 2 (0x67 prefix in 32-bit mode)
+		 * mod = 11 - no memory operand
+		 *
+		 * If address size = 2...
+		 * mod = 00, r/m = 110 - displacement field is 2 bytes
+		 *
+		 * If address size != 2...
+		 * mod != 11, r/m = 100 - SIB byte exists
+		 * mod = 00, SIB base = 101 - displacement field is 4 bytes
+		 * mod = 00, r/m = 101 - rip-relative addressing, displacement
+		 * 	field is 4 bytes
+		 */
+		mod = X86_MODRM_MOD(insn->modrm.value);
+		rm = X86_MODRM_RM(insn->modrm.value);
+		base = X86_SIB_BASE(insn->sib.value);
+		if (mod == 3)
+			goto out;
+		if (mod == 1) {
+			insn->displacement.value = get_next(signed char, insn);
+			insn->displacement.nbytes = 1;
+		} else if (insn->addr_bytes == 2) {
+			if ((mod == 0 && rm == 6) || mod == 2) {
+				insn->displacement.value =
+					 get_next(short, insn);
+				insn->displacement.nbytes = 2;
+			}
+		} else {
+			if ((mod == 0 && rm == 5) || mod == 2 ||
+			    (mod == 0 && base == 5)) {
+				insn->displacement.value = get_next(int, insn);
+				insn->displacement.nbytes = 4;
+			}
+		}
+	}
+out:
+	insn->displacement.got = 1;
+
+err_out:
+	return;
+}
+
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
+{
+	switch (insn->addr_bytes) {
+	case 2:
+		insn->moffset1.value = get_next(short, insn);
+		insn->moffset1.nbytes = 2;
+		break;
+	case 4:
+		insn->moffset1.value = get_next(int, insn);
+		insn->moffset1.nbytes = 4;
+		break;
+	case 8:
+		insn->moffset1.value = get_next(int, insn);
+		insn->moffset1.nbytes = 4;
+		insn->moffset2.value = get_next(int, insn);
+		insn->moffset2.nbytes = 4;
+		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+	insn->moffset1.got = insn->moffset2.got = 1;
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate.value = get_next(short, insn);
+		insn->immediate.nbytes = 2;
+		break;
+	case 4:
+	case 8:
+		insn->immediate.value = get_next(int, insn);
+		insn->immediate.nbytes = 4;
+		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate1.value = get_next(short, insn);
+		insn->immediate1.nbytes = 2;
+		break;
+	case 4:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		break;
+	case 8:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		insn->immediate2.value = get_next(int, insn);
+		insn->immediate2.nbytes = 4;
+		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+	insn->immediate1.got = insn->immediate2.got = 1;
+
+	return 1;
+err_out:
+	return 0;
+}
+
+/* Decode ptr16:16/32(Ap) */
+static int __get_immptr(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate1.value = get_next(short, insn);
+		insn->immediate1.nbytes = 2;
+		break;
+	case 4:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		break;
+	case 8:
+		/* ptr16:64 is not exist (no segment) */
+		return 0;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+	insn->immediate2.value = get_next(unsigned short, insn);
+	insn->immediate2.nbytes = 2;
+	insn->immediate1.got = insn->immediate2.got = 1;
+
+	return 1;
+err_out:
+	return 0;
+}
+
+/**
+ * insn_get_immediate() - Get the immediates of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * displacement bytes.
+ * Basically, most of immediates are sign-expanded. Unsigned-value can be
+ * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ */
+void insn_get_immediate(struct insn *insn)
+{
+	if (insn->immediate.got)
+		return;
+	if (!insn->displacement.got)
+		insn_get_displacement(insn);
+
+	if (inat_has_moffset(insn->attr)) {
+		if (!__get_moffset(insn))
+			goto err_out;
+		goto done;
+	}
+
+	if (!inat_has_immediate(insn->attr))
+		/* no immediates */
+		goto done;
+
+	switch (inat_immediate_size(insn->attr)) {
+	case INAT_IMM_BYTE:
+		insn->immediate.value = get_next(signed char, insn);
+		insn->immediate.nbytes = 1;
+		break;
+	case INAT_IMM_WORD:
+		insn->immediate.value = get_next(short, insn);
+		insn->immediate.nbytes = 2;
+		break;
+	case INAT_IMM_DWORD:
+		insn->immediate.value = get_next(int, insn);
+		insn->immediate.nbytes = 4;
+		break;
+	case INAT_IMM_QWORD:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		insn->immediate2.value = get_next(int, insn);
+		insn->immediate2.nbytes = 4;
+		break;
+	case INAT_IMM_PTR:
+		if (!__get_immptr(insn))
+			goto err_out;
+		break;
+	case INAT_IMM_VWORD32:
+		if (!__get_immv32(insn))
+			goto err_out;
+		break;
+	case INAT_IMM_VWORD:
+		if (!__get_immv(insn))
+			goto err_out;
+		break;
+	default:
+		/* Here, insn must have an immediate, but failed */
+		goto err_out;
+	}
+	if (inat_has_second_immediate(insn->attr)) {
+		insn->immediate2.value = get_next(signed char, insn);
+		insn->immediate2.nbytes = 1;
+	}
+done:
+	insn->immediate.got = 1;
+
+err_out:
+	return;
+}
+
+/**
+ * insn_get_length() - Get the length of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * immediates bytes.
+ */
+void insn_get_length(struct insn *insn)
+{
+	if (insn->length)
+		return;
+	if (!insn->immediate.got)
+		insn_get_immediate(insn);
+	insn->length = (unsigned char)((unsigned long)insn->next_byte
+				     - (unsigned long)insn->kaddr);
+}
diff --git a/tools/objtool/arch/x86/lib/x86-opcode-map.txt b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
new file mode 100644
index 000000000000..12e377184ee4
--- /dev/null
+++ b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
@@ -0,0 +1,1063 @@
+# x86 Opcode Maps
+#
+# This is (mostly) based on following documentations.
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
+#   (#326018-047US, June 2013)
+#
+#<Opcode maps>
+# Table: table-name
+# Referrer: escaped-name
+# AVXcode: avx-code
+# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# (or)
+# opcode: escape # escaped-name
+# EndTable
+#
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
+#<group maps>
+# GrpTable: GrpXXX
+# reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# EndTable
+#
+# AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
+#  (v): this opcode requires VEX prefix.
+#  (v1): this opcode only supports 128bit VEX.
+#
+# Last Prefix Superscripts
+#  - (66): the last prefix is 0x66
+#  - (F3): the last prefix is 0xF3
+#  - (F2): the last prefix is 0xF2
+#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
+#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
+
+Table: one byte opcode
+Referrer:
+AVXcode:
+# 0x00 - 0x0f
+00: ADD Eb,Gb
+01: ADD Ev,Gv
+02: ADD Gb,Eb
+03: ADD Gv,Ev
+04: ADD AL,Ib
+05: ADD rAX,Iz
+06: PUSH ES (i64)
+07: POP ES (i64)
+08: OR Eb,Gb
+09: OR Ev,Gv
+0a: OR Gb,Eb
+0b: OR Gv,Ev
+0c: OR AL,Ib
+0d: OR rAX,Iz
+0e: PUSH CS (i64)
+0f: escape # 2-byte escape
+# 0x10 - 0x1f
+10: ADC Eb,Gb
+11: ADC Ev,Gv
+12: ADC Gb,Eb
+13: ADC Gv,Ev
+14: ADC AL,Ib
+15: ADC rAX,Iz
+16: PUSH SS (i64)
+17: POP SS (i64)
+18: SBB Eb,Gb
+19: SBB Ev,Gv
+1a: SBB Gb,Eb
+1b: SBB Gv,Ev
+1c: SBB AL,Ib
+1d: SBB rAX,Iz
+1e: PUSH DS (i64)
+1f: POP DS (i64)
+# 0x20 - 0x2f
+20: AND Eb,Gb
+21: AND Ev,Gv
+22: AND Gb,Eb
+23: AND Gv,Ev
+24: AND AL,Ib
+25: AND rAx,Iz
+26: SEG=ES (Prefix)
+27: DAA (i64)
+28: SUB Eb,Gb
+29: SUB Ev,Gv
+2a: SUB Gb,Eb
+2b: SUB Gv,Ev
+2c: SUB AL,Ib
+2d: SUB rAX,Iz
+2e: SEG=CS (Prefix)
+2f: DAS (i64)
+# 0x30 - 0x3f
+30: XOR Eb,Gb
+31: XOR Ev,Gv
+32: XOR Gb,Eb
+33: XOR Gv,Ev
+34: XOR AL,Ib
+35: XOR rAX,Iz
+36: SEG=SS (Prefix)
+37: AAA (i64)
+38: CMP Eb,Gb
+39: CMP Ev,Gv
+3a: CMP Gb,Eb
+3b: CMP Gv,Ev
+3c: CMP AL,Ib
+3d: CMP rAX,Iz
+3e: SEG=DS (Prefix)
+3f: AAS (i64)
+# 0x40 - 0x4f
+40: INC eAX (i64) | REX (o64)
+41: INC eCX (i64) | REX.B (o64)
+42: INC eDX (i64) | REX.X (o64)
+43: INC eBX (i64) | REX.XB (o64)
+44: INC eSP (i64) | REX.R (o64)
+45: INC eBP (i64) | REX.RB (o64)
+46: INC eSI (i64) | REX.RX (o64)
+47: INC eDI (i64) | REX.RXB (o64)
+48: DEC eAX (i64) | REX.W (o64)
+49: DEC eCX (i64) | REX.WB (o64)
+4a: DEC eDX (i64) | REX.WX (o64)
+4b: DEC eBX (i64) | REX.WXB (o64)
+4c: DEC eSP (i64) | REX.WR (o64)
+4d: DEC eBP (i64) | REX.WRB (o64)
+4e: DEC eSI (i64) | REX.WRX (o64)
+4f: DEC eDI (i64) | REX.WRXB (o64)
+# 0x50 - 0x5f
+50: PUSH rAX/r8 (d64)
+51: PUSH rCX/r9 (d64)
+52: PUSH rDX/r10 (d64)
+53: PUSH rBX/r11 (d64)
+54: PUSH rSP/r12 (d64)
+55: PUSH rBP/r13 (d64)
+56: PUSH rSI/r14 (d64)
+57: PUSH rDI/r15 (d64)
+58: POP rAX/r8 (d64)
+59: POP rCX/r9 (d64)
+5a: POP rDX/r10 (d64)
+5b: POP rBX/r11 (d64)
+5c: POP rSP/r12 (d64)
+5d: POP rBP/r13 (d64)
+5e: POP rSI/r14 (d64)
+5f: POP rDI/r15 (d64)
+# 0x60 - 0x6f
+60: PUSHA/PUSHAD (i64)
+61: POPA/POPAD (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
+64: SEG=FS (Prefix)
+65: SEG=GS (Prefix)
+66: Operand-Size (Prefix)
+67: Address-Size (Prefix)
+68: PUSH Iz (d64)
+69: IMUL Gv,Ev,Iz
+6a: PUSH Ib (d64)
+6b: IMUL Gv,Ev,Ib
+6c: INS/INSB Yb,DX
+6d: INS/INSW/INSD Yz,DX
+6e: OUTS/OUTSB DX,Xb
+6f: OUTS/OUTSW/OUTSD DX,Xz
+# 0x70 - 0x7f
+70: JO Jb
+71: JNO Jb
+72: JB/JNAE/JC Jb
+73: JNB/JAE/JNC Jb
+74: JZ/JE Jb
+75: JNZ/JNE Jb
+76: JBE/JNA Jb
+77: JNBE/JA Jb
+78: JS Jb
+79: JNS Jb
+7a: JP/JPE Jb
+7b: JNP/JPO Jb
+7c: JL/JNGE Jb
+7d: JNL/JGE Jb
+7e: JLE/JNG Jb
+7f: JNLE/JG Jb
+# 0x80 - 0x8f
+80: Grp1 Eb,Ib (1A)
+81: Grp1 Ev,Iz (1A)
+82: Grp1 Eb,Ib (1A),(i64)
+83: Grp1 Ev,Ib (1A)
+84: TEST Eb,Gb
+85: TEST Ev,Gv
+86: XCHG Eb,Gb
+87: XCHG Ev,Gv
+88: MOV Eb,Gb
+89: MOV Ev,Gv
+8a: MOV Gb,Eb
+8b: MOV Gv,Ev
+8c: MOV Ev,Sw
+8d: LEA Gv,M
+8e: MOV Sw,Ew
+8f: Grp1A (1A) | POP Ev (d64)
+# 0x90 - 0x9f
+90: NOP | PAUSE (F3) | XCHG r8,rAX
+91: XCHG rCX/r9,rAX
+92: XCHG rDX/r10,rAX
+93: XCHG rBX/r11,rAX
+94: XCHG rSP/r12,rAX
+95: XCHG rBP/r13,rAX
+96: XCHG rSI/r14,rAX
+97: XCHG rDI/r15,rAX
+98: CBW/CWDE/CDQE
+99: CWD/CDQ/CQO
+9a: CALLF Ap (i64)
+9b: FWAIT/WAIT
+9c: PUSHF/D/Q Fv (d64)
+9d: POPF/D/Q Fv (d64)
+9e: SAHF
+9f: LAHF
+# 0xa0 - 0xaf
+a0: MOV AL,Ob
+a1: MOV rAX,Ov
+a2: MOV Ob,AL
+a3: MOV Ov,rAX
+a4: MOVS/B Yb,Xb
+a5: MOVS/W/D/Q Yv,Xv
+a6: CMPS/B Xb,Yb
+a7: CMPS/W/D Xv,Yv
+a8: TEST AL,Ib
+a9: TEST rAX,Iz
+aa: STOS/B Yb,AL
+ab: STOS/W/D/Q Yv,rAX
+ac: LODS/B AL,Xb
+ad: LODS/W/D/Q rAX,Xv
+ae: SCAS/B AL,Yb
+# Note: The May 2011 Intel manual shows Xv for the second parameter of the
+# next instruction but Yv is correct
+af: SCAS/W/D/Q rAX,Yv
+# 0xb0 - 0xbf
+b0: MOV AL/R8L,Ib
+b1: MOV CL/R9L,Ib
+b2: MOV DL/R10L,Ib
+b3: MOV BL/R11L,Ib
+b4: MOV AH/R12L,Ib
+b5: MOV CH/R13L,Ib
+b6: MOV DH/R14L,Ib
+b7: MOV BH/R15L,Ib
+b8: MOV rAX/r8,Iv
+b9: MOV rCX/r9,Iv
+ba: MOV rDX/r10,Iv
+bb: MOV rBX/r11,Iv
+bc: MOV rSP/r12,Iv
+bd: MOV rBP/r13,Iv
+be: MOV rSI/r14,Iv
+bf: MOV rDI/r15,Iv
+# 0xc0 - 0xcf
+c0: Grp2 Eb,Ib (1A)
+c1: Grp2 Ev,Ib (1A)
+c2: RETN Iw (f64)
+c3: RETN
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c6: Grp11A Eb,Ib (1A)
+c7: Grp11B Ev,Iz (1A)
+c8: ENTER Iw,Ib
+c9: LEAVE (d64)
+ca: RETF Iw
+cb: RETF
+cc: INT3
+cd: INT Ib
+ce: INTO (i64)
+cf: IRET/D/Q
+# 0xd0 - 0xdf
+d0: Grp2 Eb,1 (1A)
+d1: Grp2 Ev,1 (1A)
+d2: Grp2 Eb,CL (1A)
+d3: Grp2 Ev,CL (1A)
+d4: AAM Ib (i64)
+d5: AAD Ib (i64)
+d6:
+d7: XLAT/XLATB
+d8: ESC
+d9: ESC
+da: ESC
+db: ESC
+dc: ESC
+dd: ESC
+de: ESC
+df: ESC
+# 0xe0 - 0xef
+# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
+# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
+# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
+e0: LOOPNE/LOOPNZ Jb (f64)
+e1: LOOPE/LOOPZ Jb (f64)
+e2: LOOP Jb (f64)
+e3: JrCXZ Jb (f64)
+e4: IN AL,Ib
+e5: IN eAX,Ib
+e6: OUT Ib,AL
+e7: OUT Ib,eAX
+# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
+# in "near" jumps and calls is 16-bit. For CALL,
+# push of return address is 16-bit wide, RSP is decremented by 2
+# but is not truncated to 16 bits, unlike RIP.
+e8: CALL Jz (f64)
+e9: JMP-near Jz (f64)
+ea: JMP-far Ap (i64)
+eb: JMP-short Jb (f64)
+ec: IN AL,DX
+ed: IN eAX,DX
+ee: OUT DX,AL
+ef: OUT DX,eAX
+# 0xf0 - 0xff
+f0: LOCK (Prefix)
+f1:
+f2: REPNE (Prefix) | XACQUIRE (Prefix)
+f3: REP/REPE (Prefix) | XRELEASE (Prefix)
+f4: HLT
+f5: CMC
+f6: Grp3_1 Eb (1A)
+f7: Grp3_2 Ev (1A)
+f8: CLC
+f9: STC
+fa: CLI
+fb: STI
+fc: CLD
+fd: STD
+fe: Grp4 (1A)
+ff: Grp5 (1A)
+EndTable
+
+Table: 2-byte opcode (0x0f)
+Referrer: 2-byte escape
+AVXcode: 1
+# 0x0f 0x00-0x0f
+00: Grp6 (1A)
+01: Grp7 (1A)
+02: LAR Gv,Ew
+03: LSL Gv,Ew
+04:
+05: SYSCALL (o64)
+06: CLTS
+07: SYSRET (o64)
+08: INVD
+09: WBINVD
+0a:
+0b: UD2 (1B)
+0c:
+# AMD's prefetch group. Intel supports prefetchw(/1) only.
+0d: GrpP
+0e: FEMMS
+# 3DNow! uses the last imm byte as opcode extension.
+0f: 3DNow! Pq,Qq,Ib
+# 0x0f 0x10-0x1f
+# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
+# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
+# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
+# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
+# Reference A.1
+10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
+11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
+12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
+13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
+14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
+15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
+16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
+17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
+18: Grp16 (1A)
+19:
+# Intel SDM opcode map does not list MPX instructions. For now using Gv for
+# bnd registers and Ev for everything else is OK because the instruction
+# decoder does not use the information except as an indication that there is
+# a ModR/M byte.
+1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
+1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
+1c:
+1d:
+1e:
+1f: NOP Ev
+# 0x0f 0x20-0x2f
+20: MOV Rd,Cd
+21: MOV Rd,Dd
+22: MOV Cd,Rd
+23: MOV Dd,Rd
+24:
+25:
+26:
+27:
+28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
+29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
+2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
+2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
+2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
+2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
+2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
+2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
+# 0x0f 0x30-0x3f
+30: WRMSR
+31: RDTSC
+32: RDMSR
+33: RDPMC
+34: SYSENTER
+35: SYSEXIT
+36:
+37: GETSEC
+38: escape # 3-byte escape 1
+39:
+3a: escape # 3-byte escape 2
+3b:
+3c:
+3d:
+3e:
+3f:
+# 0x0f 0x40-0x4f
+40: CMOVO Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
+43: CMOVAE/NB/NC Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
+48: CMOVS Gv,Ev
+49: CMOVNS Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
+4c: CMOVL/NGE Gv,Ev
+4d: CMOVNL/GE Gv,Ev
+4e: CMOVLE/NG Gv,Ev
+4f: CMOVNLE/G Gv,Ev
+# 0x0f 0x50-0x5f
+50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
+51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
+52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
+53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
+54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
+55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
+56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
+57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
+58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
+59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
+5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
+5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
+5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
+5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
+# 0x0f 0x60-0x6f
+60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
+61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
+62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
+63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
+64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
+65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
+66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
+67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
+68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
+69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
+6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
+6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
+6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
+6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
+6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
+# 0x0f 0x70-0x7f
+70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
+71: Grp12 (1A)
+72: Grp13 (1A)
+73: Grp14 (1A)
+74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
+75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
+76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
+# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
+77: emms | vzeroupper | vzeroall
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
+7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
+7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
+7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
+# 0x0f 0x80-0x8f
+# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
+80: JO Jz (f64)
+81: JNO Jz (f64)
+82: JB/JC/JNAE Jz (f64)
+83: JAE/JNB/JNC Jz (f64)
+84: JE/JZ Jz (f64)
+85: JNE/JNZ Jz (f64)
+86: JBE/JNA Jz (f64)
+87: JA/JNBE Jz (f64)
+88: JS Jz (f64)
+89: JNS Jz (f64)
+8a: JP/JPE Jz (f64)
+8b: JNP/JPO Jz (f64)
+8c: JL/JNGE Jz (f64)
+8d: JNL/JGE Jz (f64)
+8e: JLE/JNG Jz (f64)
+8f: JNLE/JG Jz (f64)
+# 0x0f 0x90-0x9f
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
+94: SETE/Z Eb
+95: SETNE/NZ Eb
+96: SETBE/NA Eb
+97: SETA/NBE Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
+9a: SETP/PE Eb
+9b: SETNP/PO Eb
+9c: SETL/NGE Eb
+9d: SETNL/GE Eb
+9e: SETLE/NG Eb
+9f: SETNLE/G Eb
+# 0x0f 0xa0-0xaf
+a0: PUSH FS (d64)
+a1: POP FS (d64)
+a2: CPUID
+a3: BT Ev,Gv
+a4: SHLD Ev,Gv,Ib
+a5: SHLD Ev,Gv,CL
+a6: GrpPDLK
+a7: GrpRNG
+a8: PUSH GS (d64)
+a9: POP GS (d64)
+aa: RSM
+ab: BTS Ev,Gv
+ac: SHRD Ev,Gv,Ib
+ad: SHRD Ev,Gv,CL
+ae: Grp15 (1A),(1C)
+af: IMUL Gv,Ev
+# 0x0f 0xb0-0xbf
+b0: CMPXCHG Eb,Gb
+b1: CMPXCHG Ev,Gv
+b2: LSS Gv,Mp
+b3: BTR Ev,Gv
+b4: LFS Gv,Mp
+b5: LGS Gv,Mp
+b6: MOVZX Gv,Eb
+b7: MOVZX Gv,Ew
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
+b9: Grp10 (1A)
+ba: Grp8 Ev,Ib (1A)
+bb: BTC Ev,Gv
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
+be: MOVSX Gv,Eb
+bf: MOVSX Gv,Ew
+# 0x0f 0xc0-0xcf
+c0: XADD Eb,Gb
+c1: XADD Ev,Gv
+c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
+c3: movnti My,Gy
+c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
+c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
+c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
+c7: Grp9 (1A)
+c8: BSWAP RAX/EAX/R8/R8D
+c9: BSWAP RCX/ECX/R9/R9D
+ca: BSWAP RDX/EDX/R10/R10D
+cb: BSWAP RBX/EBX/R11/R11D
+cc: BSWAP RSP/ESP/R12/R12D
+cd: BSWAP RBP/EBP/R13/R13D
+ce: BSWAP RSI/ESI/R14/R14D
+cf: BSWAP RDI/EDI/R15/R15D
+# 0x0f 0xd0-0xdf
+d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
+d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
+d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
+d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
+d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
+d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
+d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
+d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
+d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
+da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
+dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
+dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
+de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
+# 0x0f 0xe0-0xef
+e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
+e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
+e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
+e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
+e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
+e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
+e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
+e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
+e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
+ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
+ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
+ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
+ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
+# 0x0f 0xf0-0xff
+f0: vlddqu Vx,Mx (F2)
+f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
+f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
+f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
+f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
+f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
+f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
+f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
+f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
+f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
+fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
+fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
+fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
+fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
+fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
+ff:
+EndTable
+
+Table: 3-byte opcode 1 (0x0f 0x38)
+Referrer: 3-byte escape 1
+AVXcode: 2
+# 0x0f 0x38 0x00-0x0f
+00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
+01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
+02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
+03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
+04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
+05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
+06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
+07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
+08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
+09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
+0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
+0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
+0c: vpermilps Vx,Hx,Wx (66),(v)
+0d: vpermilpd Vx,Hx,Wx (66),(v)
+0e: vtestps Vx,Wx (66),(v)
+0f: vtestpd Vx,Wx (66),(v)
+# 0x0f 0x38 0x10-0x1f
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
+17: vptest Vx,Wx (66)
+18: vbroadcastss Vx,Wd (66),(v)
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
+1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
+1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
+1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
+1f: vpabsq Vx,Wx (66),(ev)
+# 0x0f 0x38 0x20-0x2f
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
+2b: vpackusdw Vx,Hx,Wx (66),(v1)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
+2e: vmaskmovps Mx,Hx,Vx (66),(v)
+2f: vmaskmovpd Mx,Hx,Vx (66),(v)
+# 0x0f 0x38 0x30-0x3f
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
+37: vpcmpgtq Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
+3c: vpmaxsb Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
+3e: vpmaxuw Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
+# 0x0f 0x38 0x40-0x8f
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
+41: vphminposuw Vdq,Wdq (66),(v1)
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
+45: vpsrlvd/q Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
+47: vpsllvd/q Vx,Hx,Wx (66),(v)
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
+58: vpbroadcastd Vx,Wx (66),(v)
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
+78: vpbroadcastb Vx,Wx (66),(v)
+79: vpbroadcastw Vx,Wx (66),(v)
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
+80: INVEPT Gy,Mdq (66)
+81: INVPID Gy,Mdq (66)
+82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
+8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
+8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
+# 0x0f 0x38 0x90-0xbf (FMA)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
+92: vgatherdps/d Vx,Hx,Wx (66),(v)
+93: vgatherqps/d Vx,Hx,Wx (66),(v)
+94:
+95:
+96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
+97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
+98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
+99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
+9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
+9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
+a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
+a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
+a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
+a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
+ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
+af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
+b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
+b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
+b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
+b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
+bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
+bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
+bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+# 0x0f 0x38 0xc0-0xff
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
+c9: sha1msg1 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
+db: VAESIMC Vdq,Wdq (66),(v1)
+dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
+dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
+de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
+df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
+f2: ANDN Gy,By,Ey (v)
+f3: Grp17 (1A)
+f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
+f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
+EndTable
+
+Table: 3-byte opcode 2 (0x0f 0x3a)
+Referrer: 3-byte escape 2
+AVXcode: 3
+# 0x0f 0x3a 0x00-0xff
+00: vpermq Vqq,Wqq,Ib (66),(v)
+01: vpermpd Vqq,Wqq,Ib (66),(v)
+02: vpblendd Vx,Hx,Wx,Ib (66),(v)
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
+04: vpermilps Vx,Wx,Ib (66),(v)
+05: vpermilpd Vx,Wx,Ib (66),(v)
+06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
+07:
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
+0c: vblendps Vx,Hx,Wx,Ib (66)
+0d: vblendpd Vx,Hx,Wx,Ib (66)
+0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
+0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
+14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
+15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
+16: vpextrd/q Ey,Vdq,Ib (66),(v1)
+17: vextractps Ed,Vdq,Ib (66),(v1)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
+20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
+21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
+22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
+40: vdpps Vx,Hx,Wx,Ib (66)
+41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
+46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
+4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
+4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
+4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
+60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
+61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
+62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
+63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
+cc: sha1rnds4 Vdq,Wdq,Ib
+df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
+f0: RORX Gy,Ey,Ib (F2),(v)
+EndTable
+
+GrpTable: Grp1
+0: ADD
+1: OR
+2: ADC
+3: SBB
+4: AND
+5: SUB
+6: XOR
+7: CMP
+EndTable
+
+GrpTable: Grp1A
+0: POP
+EndTable
+
+GrpTable: Grp2
+0: ROL
+1: ROR
+2: RCL
+3: RCR
+4: SHL/SAL
+5: SHR
+6:
+7: SAR
+EndTable
+
+GrpTable: Grp3_1
+0: TEST Eb,Ib
+1:
+2: NOT Eb
+3: NEG Eb
+4: MUL AL,Eb
+5: IMUL AL,Eb
+6: DIV AL,Eb
+7: IDIV AL,Eb
+EndTable
+
+GrpTable: Grp3_2
+0: TEST Ev,Iz
+1:
+2: NOT Ev
+3: NEG Ev
+4: MUL rAX,Ev
+5: IMUL rAX,Ev
+6: DIV rAX,Ev
+7: IDIV rAX,Ev
+EndTable
+
+GrpTable: Grp4
+0: INC Eb
+1: DEC Eb
+EndTable
+
+GrpTable: Grp5
+0: INC Ev
+1: DEC Ev
+# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
+2: CALLN Ev (f64)
+3: CALLF Ep
+4: JMPN Ev (f64)
+5: JMPF Mp
+6: PUSH Ev (d64)
+7:
+EndTable
+
+GrpTable: Grp6
+0: SLDT Rv/Mw
+1: STR Rv/Mw
+2: LLDT Ew
+3: LTR Ew
+4: VERR Ew
+5: VERW Ew
+EndTable
+
+GrpTable: Grp7
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
+3: LIDT Ms
+4: SMSW Mw/Rv
+5: rdpkru (110),(11B) | wrpkru (111),(11B)
+6: LMSW Ew
+7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
+EndTable
+
+GrpTable: Grp8
+4: BT
+5: BTS
+6: BTR
+7: BTC
+EndTable
+
+GrpTable: Grp9
+1: CMPXCHG8B/16B Mq/Mdq
+3: xrstors
+4: xsavec
+5: xsaves
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
+7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
+EndTable
+
+GrpTable: Grp10
+EndTable
+
+# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
+GrpTable: Grp11A
+0: MOV Eb,Ib
+7: XABORT Ib (000),(11B)
+EndTable
+
+GrpTable: Grp11B
+0: MOV Eb,Iz
+7: XBEGIN Jz (000),(11B)
+EndTable
+
+GrpTable: Grp12
+2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
+4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
+6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
+2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
+6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp14
+2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
+3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
+6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
+7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp15
+0: fxsave | RDFSBASE Ry (F3),(11B)
+1: fxstor | RDGSBASE Ry (F3),(11B)
+2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
+3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
+4: XSAVE | ptwrite Ey (F3),(11B)
+5: XRSTOR | lfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B)
+7: clflush | clflushopt (66) | sfence (11B)
+EndTable
+
+GrpTable: Grp16
+0: prefetch NTA
+1: prefetch T0
+2: prefetch T1
+3: prefetch T2
+EndTable
+
+GrpTable: Grp17
+1: BLSR By,Ey (v)
+2: BLSMSK By,Ey (v)
+3: BLSI By,Ey (v)
+EndTable
+
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
+# AMD's Prefetch Group
+GrpTable: GrpP
+0: PREFETCH
+1: PREFETCHW
+EndTable
+
+GrpTable: GrpPDLK
+0: MONTMUL
+1: XSHA1
+2: XSHA2
+EndTable
+
+GrpTable: GrpRNG
+0: xstore-rng
+1: xcrypt-ecb
+2: xcrypt-cbc
+4: xcrypt-cfb
+5: xcrypt-ofb
+EndTable
diff --git a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
new file mode 100644
index 000000000000..b02a36b2c14f
--- /dev/null
+++ b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
@@ -0,0 +1,393 @@
+#!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
+# gen-insn-attr-x86.awk: Instruction attribute table generator
+# Written by Masami Hiramatsu <mhiramat@redhat.com>
+#
+# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
+
+# Awk implementation sanity check
+function check_awk_implement() {
+	if (sprintf("%x", 0) != "0")
+		return "Your awk has a printf-format problem."
+	return ""
+}
+
+# Clear working vars
+function clear_vars() {
+	delete table
+	delete lptable2
+	delete lptable1
+	delete lptable3
+	eid = -1 # escape id
+	gid = -1 # group id
+	aid = -1 # AVX id
+	tname = ""
+}
+
+BEGIN {
+	# Implementation error checking
+	awkchecked = check_awk_implement()
+	if (awkchecked != "") {
+		print "Error: " awkchecked > "/dev/stderr"
+		print "Please try to use gawk." > "/dev/stderr"
+		exit 1
+	}
+
+	# Setup generating tables
+	print "/* x86 opcode map generated from x86-opcode-map.txt */"
+	print "/* Do not change this code. */\n"
+	ggid = 1
+	geid = 1
+	gaid = 0
+	delete etable
+	delete gtable
+	delete atable
+
+	opnd_expr = "^[A-Za-z/]"
+	ext_expr = "^\\("
+	sep_expr = "^\\|$"
+	group_expr = "^Grp[0-9A-Za-z]+"
+
+	imm_expr = "^[IJAOL][a-z]"
+	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
+	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
+	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
+	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
+	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
+	imm_flag["Ob"] = "INAT_MOFFSET"
+	imm_flag["Ov"] = "INAT_MOFFSET"
+	imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+
+	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
+	force64_expr = "\\([df]64\\)"
+	rex_expr = "^REX(\\.[XRWB]+)*"
+	fpu_expr = "^ESC" # TODO
+
+	lprefix1_expr = "\\((66|!F3)\\)"
+	lprefix2_expr = "\\(F3\\)"
+	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
+	max_lprefix = 4
+
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
+	# accepts VEX prefix
+	vexok_opcode_expr = "^[vk].*"
+	vexok_expr = "\\(v1\\)"
+	# All opcodes with (v) superscript supports *only* VEX prefix
+	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
+
+	prefix_expr = "\\(Prefix\\)"
+	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
+	prefix_num["REPNE"] = "INAT_PFX_REPNE"
+	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
+	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
+	prefix_num["LOCK"] = "INAT_PFX_LOCK"
+	prefix_num["SEG=CS"] = "INAT_PFX_CS"
+	prefix_num["SEG=DS"] = "INAT_PFX_DS"
+	prefix_num["SEG=ES"] = "INAT_PFX_ES"
+	prefix_num["SEG=FS"] = "INAT_PFX_FS"
+	prefix_num["SEG=GS"] = "INAT_PFX_GS"
+	prefix_num["SEG=SS"] = "INAT_PFX_SS"
+	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
+	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
+	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
+
+	clear_vars()
+}
+
+function semantic_error(msg) {
+	print "Semantic error at " NR ": " msg > "/dev/stderr"
+	exit 1
+}
+
+function debug(msg) {
+	print "DEBUG: " msg
+}
+
+function array_size(arr,   i,c) {
+	c = 0
+	for (i in arr)
+		c++
+	return c
+}
+
+/^Table:/ {
+	print "/* " $0 " */"
+	if (tname != "")
+		semantic_error("Hit Table: before EndTable:.");
+}
+
+/^Referrer:/ {
+	if (NF != 1) {
+		# escape opcode table
+		ref = ""
+		for (i = 2; i <= NF; i++)
+			ref = ref $i
+		eid = escape[ref]
+		tname = sprintf("inat_escape_table_%d", eid)
+	}
+}
+
+/^AVXcode:/ {
+	if (NF != 1) {
+		# AVX/escape opcode table
+		aid = $2
+		if (gaid <= aid)
+			gaid = aid + 1
+		if (tname == "")	# AVX only opcode table
+			tname = sprintf("inat_avx_table_%d", $2)
+	}
+	if (aid == -1 && eid == -1)	# primary opcode table
+		tname = "inat_primary_table"
+}
+
+/^GrpTable:/ {
+	print "/* " $0 " */"
+	if (!($2 in group))
+		semantic_error("No group: " $2 )
+	gid = group[$2]
+	tname = "inat_group_table_" gid
+}
+
+function print_table(tbl,name,fmt,n)
+{
+	print "const insn_attr_t " name " = {"
+	for (i = 0; i < n; i++) {
+		id = sprintf(fmt, i)
+		if (tbl[id])
+			print "	[" id "] = " tbl[id] ","
+	}
+	print "};"
+}
+
+/^EndTable/ {
+	if (gid != -1) {
+		# print group tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,3] = tname "_3"
+		}
+	} else {
+		# print primary/escaped tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,0] = tname
+			if (aid >= 0)
+				atable[aid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,1] = tname "_1"
+			if (aid >= 0)
+				atable[aid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,2] = tname "_2"
+			if (aid >= 0)
+				atable[aid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,3] = tname "_3"
+			if (aid >= 0)
+				atable[aid,3] = tname "_3"
+		}
+	}
+	print ""
+	clear_vars()
+}
+
+function add_flags(old,new) {
+	if (old && new)
+		return old " | " new
+	else if (old)
+		return old
+	else
+		return new
+}
+
+# convert operands to flags.
+function convert_operands(count,opnd,       i,j,imm,mod)
+{
+	imm = null
+	mod = null
+	for (j = 1; j <= count; j++) {
+		i = opnd[j]
+		if (match(i, imm_expr) == 1) {
+			if (!imm_flag[i])
+				semantic_error("Unknown imm opnd: " i)
+			if (imm) {
+				if (i != "Ib")
+					semantic_error("Second IMM error")
+				imm = add_flags(imm, "INAT_SCNDIMM")
+			} else
+				imm = imm_flag[i]
+		} else if (match(i, modrm_expr))
+			mod = "INAT_MODRM"
+	}
+	return add_flags(imm, mod)
+}
+
+/^[0-9a-f]+\:/ {
+	if (NR == 1)
+		next
+	# get index
+	idx = "0x" substr($1, 1, index($1,":") - 1)
+	if (idx in table)
+		semantic_error("Redefine " idx " in " tname)
+
+	# check if escaped opcode
+	if ("escape" == $2) {
+		if ($3 != "#")
+			semantic_error("No escaped name")
+		ref = ""
+		for (i = 4; i <= NF; i++)
+			ref = ref $i
+		if (ref in escape)
+			semantic_error("Redefine escape (" ref ")")
+		escape[ref] = geid
+		geid++
+		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
+		next
+	}
+
+	variant = null
+	# converts
+	i = 2
+	while (i <= NF) {
+		opcode = $(i++)
+		delete opnds
+		ext = null
+		flags = null
+		opnd = null
+		# parse one opcode
+		if (match($i, opnd_expr)) {
+			opnd = $i
+			count = split($(i++), opnds, ",")
+			flags = convert_operands(count, opnds)
+		}
+		if (match($i, ext_expr))
+			ext = $(i++)
+		if (match($i, sep_expr))
+			i++
+		else if (i < NF)
+			semantic_error($i " is not a separator")
+
+		# check if group opcode
+		if (match(opcode, group_expr)) {
+			if (!(opcode in group)) {
+				group[opcode] = ggid
+				ggid++
+			}
+			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
+		}
+		# check force(or default) 64bit
+		if (match(ext, force64_expr))
+			flags = add_flags(flags, "INAT_FORCE64")
+
+		# check REX prefix
+		if (match(opcode, rex_expr))
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
+
+		# check coprocessor escape : TODO
+		if (match(opcode, fpu_expr))
+			flags = add_flags(flags, "INAT_MODRM")
+
+		# check VEX codes
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
+		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
+			flags = add_flags(flags, "INAT_VEXOK")
+
+		# check prefixes
+		if (match(ext, prefix_expr)) {
+			if (!prefix_num[opcode])
+				semantic_error("Unknown prefix: " opcode)
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
+		}
+		if (length(flags) == 0)
+			continue
+		# check if last prefix
+		if (match(ext, lprefix1_expr)) {
+			lptable1[idx] = add_flags(lptable1[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, lprefix2_expr)) {
+			lptable2[idx] = add_flags(lptable2[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, lprefix3_expr)) {
+			lptable3[idx] = add_flags(lptable3[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (!match(ext, lprefix_expr)){
+			table[idx] = add_flags(table[idx],flags)
+		}
+	}
+	if (variant)
+		table[idx] = add_flags(table[idx],variant)
+}
+
+END {
+	if (awkchecked != "")
+		exit 1
+	# print escape opcode map's array
+	print "/* Escape opcode map array */"
+	print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < geid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (etable[i,j])
+				print "	["i"]["j"] = "etable[i,j]","
+	print "};\n"
+	# print group opcode map's array
+	print "/* Group opcode map array */"
+	print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < ggid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (gtable[i,j])
+				print "	["i"]["j"] = "gtable[i,j]","
+	print "};\n"
+	# print AVX opcode map's array
+	print "/* AVX opcode map array */"
+	print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < gaid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (atable[i,j])
+				print "	["i"]["j"] = "atable[i,j]","
+	print "};"
+}
+
diff --git a/tools/objtool/orc.h b/tools/objtool/orc.h
index a4139e386ef3..b0e92a6d0903 100644
--- a/tools/objtool/orc.h
+++ b/tools/objtool/orc.h
@@ -18,7 +18,7 @@
 #ifndef _ORC_H
 #define _ORC_H
 
-#include "orc_types.h"
+#include <asm/orc_types.h>
 
 struct objtool_file;
 
diff --git a/tools/objtool/orc_types.h b/tools/objtool/orc_types.h
deleted file mode 100644
index 9c9dc579bd7d..000000000000
--- a/tools/objtool/orc_types.h
+++ /dev/null
@@ -1,107 +0,0 @@
-/*
- * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _ORC_TYPES_H
-#define _ORC_TYPES_H
-
-#include <linux/types.h>
-#include <linux/compiler.h>
-
-/*
- * The ORC_REG_* registers are base registers which are used to find other
- * registers on the stack.
- *
- * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
- * address of the previous frame: the caller's SP before it called the current
- * function.
- *
- * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
- * the current frame.
- *
- * The most commonly used base registers are SP and BP -- which the previous SP
- * is usually based on -- and PREV_SP and UNDEFINED -- which the previous BP is
- * usually based on.
- *
- * The rest of the base registers are needed for special cases like entry code
- * and GCC realigned stacks.
- */
-#define ORC_REG_UNDEFINED		0
-#define ORC_REG_PREV_SP			1
-#define ORC_REG_DX			2
-#define ORC_REG_DI			3
-#define ORC_REG_BP			4
-#define ORC_REG_SP			5
-#define ORC_REG_R10			6
-#define ORC_REG_R13			7
-#define ORC_REG_BP_INDIRECT		8
-#define ORC_REG_SP_INDIRECT		9
-#define ORC_REG_MAX			15
-
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_SAVE		3
-#define UNWIND_HINT_TYPE_RESTORE	4
-
-#ifndef __ASSEMBLY__
-/*
- * This struct is more or less a vastly simplified version of the DWARF Call
- * Frame Information standard.  It contains only the necessary parts of DWARF
- * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
- * unwinder how to find the previous SP and BP (and sometimes entry regs) on
- * the stack for a given code address.  Each instance of the struct corresponds
- * to one or more code locations.
- */
-struct orc_entry {
-	s16		sp_offset;
-	s16		bp_offset;
-	unsigned	sp_reg:4;
-	unsigned	bp_reg:4;
-	unsigned	type:2;
-} __packed;
-
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-};
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ORC_TYPES_H */
-- 
cgit v1.2.3


From 3bd51c5a371de917e4e7401c9df006b5998579df Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Mon, 6 Nov 2017 07:21:51 -0600
Subject: objtool: Move kernel headers/code sync check to a script

Replace the nasty diff checks in the objtool Makefile with a clean bash
script, and make the warnings more specific.

Heavily inspired by tools/perf/check-headers.sh.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/ab015f15ccd8c0c6008493c3c6ee3d495eaf2927.1509974346.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/objtool/Makefile      | 16 +---------------
 tools/objtool/sync-check.sh | 29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 15 deletions(-)
 create mode 100755 tools/objtool/sync-check.sh

(limited to 'tools')

diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index c6a19d946ec1..6aaed251b4ed 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -43,22 +43,8 @@ include $(srctree)/tools/build/Makefile.include
 $(OBJTOOL_IN): fixdep FORCE
 	@$(MAKE) $(build)=objtool
 
-# Busybox's diff doesn't have -I, avoid warning in that case
-#
 $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
-	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
-	test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
-	diff arch/x86/lib/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
-	diff arch/x86/lib/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
-	diff arch/x86/lib/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
-	diff arch/x86/tools/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
-	diff arch/x86/include/asm/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
-	diff arch/x86/include/asm/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
-	diff arch/x86/include/asm/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
-	|| echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
-	@(test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
-	diff ../../arch/x86/include/asm/orc_types.h arch/x86/include/asm/orc_types.h >/dev/null) \
-	|| echo "warning: objtool: orc_types.h differs from kernel" >&2 )) || true
+	@./sync-check.sh
 	$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
 
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
new file mode 100755
index 000000000000..1470e74e9d66
--- /dev/null
+++ b/tools/objtool/sync-check.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+FILES='
+arch/x86/lib/insn.c
+arch/x86/lib/inat.c
+arch/x86/lib/x86-opcode-map.txt
+arch/x86/tools/gen-insn-attr-x86.awk
+arch/x86/include/asm/insn.h
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/inat_types.h
+arch/x86/include/asm/orc_types.h
+'
+
+check()
+{
+	local file=$1
+
+	diff $file ../../$file > /dev/null ||
+		echo "Warning: synced file at 'tools/objtool/$file' differs from latest kernel version at '$file'"
+}
+
+if [ ! -d ../../kernel ] || [ ! -d ../../tools ] || [ ! -d ../objtool ]; then
+	exit 0
+fi
+
+for i in $FILES; do
+  check $i
+done
-- 
cgit v1.2.3


From 9eb719855f6c9b21eb5889d9ac2ca1c60527ad89 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 7 Nov 2017 21:01:52 -0600
Subject: objtool: Fix cross-build

Stephen Rothwell reported this cross-compilation build failure:

| In file included from orc_dump.c:19:0:
| orc.h:21:10: fatal error: asm/orc_types.h: No such file or directory
| ...

Caused by:

  6a77cff819ae ("objtool: Move synced files to their original relative locations")

Use the proper arch header files location, not the host-arch location.

Bisected-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Linux-Next Mailing List <linux-next@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20171108030152.bd76eahiwjwjt3kp@treble
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/objtool/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 6aaed251b4ed..0f94af3ccaaa 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -27,7 +27,7 @@ all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-	    -I$(srctree)/tools/objtool/arch/$(HOSTARCH)/include
+	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
 CFLAGS   += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
-- 
cgit v1.2.3


From 41cb3301c04d7f0b046ed296a34ef261c456dde8 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Tue, 7 Nov 2017 15:48:21 -0700
Subject: tools/testing/nvdimm: stricter bounds checking for error injection
 commands

Ensure that the in/out sizes passed in the nd_cmd_package are sane for
the fixed output size commands (i.e. inject error and clear injected
error).

Reported-by: Dariusz Dokupil <dariusz.dokupil@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 79c5cb23693f..edab68c2e221 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -488,7 +488,7 @@ static int nfit_test_cmd_ars_error_inject(struct nfit_test *t,
 {
 	int rc;
 
-	if (buf_len < sizeof(*err_inj)) {
+	if (buf_len != sizeof(*err_inj)) {
 		rc = -EINVAL;
 		goto err;
 	}
@@ -519,7 +519,7 @@ static int nfit_test_cmd_ars_inject_clear(struct nfit_test *t,
 {
 	int rc;
 
-	if (buf_len < sizeof(*err_clr)) {
+	if (buf_len != sizeof(*err_clr)) {
 		rc = -EINVAL;
 		goto err;
 	}
-- 
cgit v1.2.3


From 77fad8bfb1d2f8225b05e4ea34457875fcfae37e Mon Sep 17 00:00:00 2001
From: Gustavo Romero <gromero@linux.vnet.ibm.com>
Date: Wed, 1 Nov 2017 15:23:41 -0400
Subject: selftests/powerpc: Check FP/VEC on exception in TM

Add a self test to check if FP/VEC/VSX registers are sane (restored
correctly) after a FP/VEC/VSX unavailable exception is caught during a
transaction.

This test checks all possibilities in a thread regarding the combination
of MSR.[FP|VEC] states in a thread and for each scenario raises a
FP/VEC/VSX unavailable exception in transactional state, verifying if
vs0 and vs32 registers, which are representatives of FP/VEC/VSX reg
sets, are not corrupted.

Signed-off-by: Gustavo Romero <gromero@linux.vnet.ibm.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/tm/.gitignore      |   1 +
 tools/testing/selftests/powerpc/tm/Makefile        |   3 +-
 .../testing/selftests/powerpc/tm/tm-unavailable.c  | 371 +++++++++++++++++++++
 tools/testing/selftests/powerpc/tm/tm.h            |   5 +
 4 files changed, 379 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/powerpc/tm/tm-unavailable.c

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 2f1f7b013293..241a4a4ee0e4 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -12,3 +12,4 @@ tm-signal-context-chk-gpr
 tm-signal-context-chk-vmx
 tm-signal-context-chk-vsx
 tm-vmx-unavail
+tm-unavailable
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 7bfcd454fb2a..24855c0eee53 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -2,7 +2,7 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu
 	tm-signal-context-chk-vmx tm-signal-context-chk-vsx
 
 TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
-	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \
+	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable \
 	$(SIGNAL_CONTEXT_CHK_TESTS)
 
 include ../../lib.mk
@@ -16,6 +16,7 @@ $(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-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 
 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S
diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
new file mode 100644
index 000000000000..96c37f84ce54
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
@@ -0,0 +1,371 @@
+/*
+ * Copyright 2017, Gustavo Romero, Breno Leitao, Cyril Bur, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Force FP, VEC and VSX unavailable exception during transaction in all
+ * possible scenarios regarding the MSR.FP and MSR.VEC state, e.g. when FP
+ * is enable and VEC is disable, when FP is disable and VEC is enable, and
+ * so on. Then we check if the restored state is correctly set for the
+ * FP and VEC registers to the previous state we set just before we entered
+ * in TM, i.e. we check if it corrupts somehow the recheckpointed FP and
+ * VEC/Altivec registers on abortion due to an unavailable exception in TM.
+ * N.B. In this test we do not test all the FP/Altivec/VSX registers for
+ * corruption, but only for registers vs0 and vs32, which are respectively
+ * representatives of FP and VEC/Altivec reg sets.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sched.h>
+
+#include "tm.h"
+
+#define DEBUG 0
+
+/* Unavailable exceptions to test in HTM */
+#define FP_UNA_EXCEPTION	0
+#define VEC_UNA_EXCEPTION	1
+#define VSX_UNA_EXCEPTION	2
+
+#define NUM_EXCEPTIONS		3
+
+struct Flags {
+	int touch_fp;
+	int touch_vec;
+	int result;
+	int exception;
+} flags;
+
+bool expecting_failure(void)
+{
+	if (flags.touch_fp && flags.exception == FP_UNA_EXCEPTION)
+		return false;
+
+	if (flags.touch_vec && flags.exception == VEC_UNA_EXCEPTION)
+		return false;
+
+	/*
+	 * If both FP and VEC are touched it does not mean that touching VSX
+	 * won't raise an exception. However since FP and VEC state are already
+	 * correctly loaded, the transaction is not aborted (i.e.
+	 * treclaimed/trecheckpointed) and MSR.VSX is just set as 1, so a TM
+	 * failure is not expected also in this case.
+	 */
+	if ((flags.touch_fp && flags.touch_vec) &&
+	     flags.exception == VSX_UNA_EXCEPTION)
+		return false;
+
+	return true;
+}
+
+/* Check if failure occurred whilst in transaction. */
+bool is_failure(uint64_t condition_reg)
+{
+	/*
+	 * When failure handling occurs, CR0 is set to 0b1010 (0xa). Otherwise
+	 * transaction completes without failure and hence reaches out 'tend.'
+	 * that sets CR0 to 0b0100 (0x4).
+	 */
+	return ((condition_reg >> 28) & 0xa) == 0xa;
+}
+
+void *ping(void *input)
+{
+
+	/*
+	 * Expected values for vs0 and vs32 after a TM failure. They must never
+	 * change, otherwise they got corrupted.
+	 */
+	uint64_t high_vs0 = 0x5555555555555555;
+	uint64_t low_vs0 = 0xffffffffffffffff;
+	uint64_t high_vs32 = 0x5555555555555555;
+	uint64_t low_vs32 = 0xffffffffffffffff;
+
+	/* Counter for busy wait */
+	uint64_t counter = 0x1ff000000;
+
+	/*
+	 * Variable to keep a copy of CR register content taken just after we
+	 * leave the transactional state.
+	 */
+	uint64_t cr_ = 0;
+
+	/*
+	 * Wait a bit so thread can get its name "ping". This is not important
+	 * to reproduce the issue but it's nice to have for systemtap debugging.
+	 */
+	if (DEBUG)
+		sleep(1);
+
+	printf("If MSR.FP=%d MSR.VEC=%d: ", flags.touch_fp, flags.touch_vec);
+
+	if (flags.exception != FP_UNA_EXCEPTION &&
+	    flags.exception != VEC_UNA_EXCEPTION &&
+	    flags.exception != VSX_UNA_EXCEPTION) {
+		printf("No valid exception specified to test.\n");
+		return NULL;
+	}
+
+	asm (
+		/* Prepare to merge low and high. */
+		"	mtvsrd		33, %[high_vs0]		;"
+		"	mtvsrd		34, %[low_vs0]		;"
+
+		/*
+		 * Adjust VS0 expected value after an TM failure,
+		 * i.e. vs0 = 0x5555555555555555555FFFFFFFFFFFFFFFF
+		 */
+		"	xxmrghd		0, 33, 34		;"
+
+		/*
+		 * Adjust VS32 expected value after an TM failure,
+		 * i.e. vs32 = 0x5555555555555555555FFFFFFFFFFFFFFFF
+		 */
+		"	xxmrghd		32, 33, 34		;"
+
+		/*
+		 * Wait an amount of context switches so load_fp and load_vec
+		 * overflow and MSR.FP, MSR.VEC, and MSR.VSX become zero (off).
+		 */
+		"	mtctr		%[counter]		;"
+
+		/* Decrement CTR branch if CTR non zero. */
+		"1:	bdnz 1b					;"
+
+		/*
+		 * Check if we want to touch FP prior to the test in order
+		 * to set MSR.FP = 1 before provoking an unavailable
+		 * exception in TM.
+		 */
+		"	cmpldi		%[touch_fp], 0		;"
+		"	beq		no_fp			;"
+		"	fadd		10, 10, 10		;"
+		"no_fp:						;"
+
+		/*
+		 * Check if we want to touch VEC prior to the test in order
+		 * to set MSR.VEC = 1 before provoking an unavailable
+		 * exception in TM.
+		 */
+		"	cmpldi		%[touch_vec], 0		;"
+		"	beq		no_vec			;"
+		"	vaddcuw		10, 10, 10		;"
+		"no_vec:					;"
+
+		/*
+		 * Perhaps it would be a better idea to do the
+		 * compares outside transactional context and simply
+		 * duplicate code.
+		 */
+		"	tbegin.					;"
+		"	beq		trans_fail		;"
+
+		/* Do we do FP Unavailable? */
+		"	cmpldi		%[exception], %[ex_fp]	;"
+		"	bne		1f			;"
+		"	fadd		10, 10, 10		;"
+		"	b		done			;"
+
+		/* Do we do VEC Unavailable? */
+		"1:	cmpldi		%[exception], %[ex_vec]	;"
+		"	bne		2f			;"
+		"	vaddcuw		10, 10, 10		;"
+		"	b		done			;"
+
+		/*
+		 * Not FP or VEC, therefore VSX. Ensure this
+		 * instruction always generates a VSX Unavailable.
+		 * ISA 3.0 is tricky here.
+		 * (xxmrghd will on ISA 2.07 and ISA 3.0)
+		 */
+		"2:	xxmrghd		10, 10, 10		;"
+
+		"done:	tend. ;"
+
+		"trans_fail: ;"
+
+		/* Give values back to C. */
+		"	mfvsrd		%[high_vs0], 0		;"
+		"	xxsldwi		3, 0, 0, 2		;"
+		"	mfvsrd		%[low_vs0], 3		;"
+		"	mfvsrd		%[high_vs32], 32	;"
+		"	xxsldwi		3, 32, 32, 2		;"
+		"	mfvsrd		%[low_vs32], 3		;"
+
+		/* Give CR back to C so that it can check what happened. */
+		"	mfcr		%[cr_]		;"
+
+		: [high_vs0]  "+r" (high_vs0),
+		  [low_vs0]   "+r" (low_vs0),
+		  [high_vs32] "=r" (high_vs32),
+		  [low_vs32]  "=r" (low_vs32),
+		  [cr_]       "+r" (cr_)
+		: [touch_fp]  "r"  (flags.touch_fp),
+		  [touch_vec] "r"  (flags.touch_vec),
+		  [exception] "r"  (flags.exception),
+		  [ex_fp]     "i"  (FP_UNA_EXCEPTION),
+		  [ex_vec]    "i"  (VEC_UNA_EXCEPTION),
+		  [ex_vsx]    "i"  (VSX_UNA_EXCEPTION),
+		  [counter]   "r"  (counter)
+
+		: "cr0", "ctr", "v10", "vs0", "vs10", "vs3", "vs32", "vs33",
+		  "vs34", "fr10"
+
+		);
+
+	/*
+	 * Check if we were expecting a failure and it did not occur by checking
+	 * CR0 state just after we leave the transaction. Either way we check if
+	 * vs0 or vs32 got corrupted.
+	 */
+	if (expecting_failure() && !is_failure(cr_)) {
+		printf("\n\tExpecting the transaction to fail, %s",
+			"but it didn't\n\t");
+		flags.result++;
+	}
+
+	/* Check if we were not expecting a failure and a it occurred. */
+	if (!expecting_failure() && is_failure(cr_)) {
+		printf("\n\tUnexpected transaction failure 0x%02lx\n\t",
+			failure_code());
+		return (void *) -1;
+	}
+
+	/*
+	 * Check if TM failed due to the cause we were expecting. 0xda is a
+	 * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause.
+	 */
+	if (is_failure(cr_) && !failure_is_unavailable()) {
+		printf("\n\tUnexpected failure cause 0x%02lx\n\t",
+			failure_code());
+		return (void *) -1;
+	}
+
+	/* 0x4 is a success and 0xa is a fail. See comment in is_failure(). */
+	if (DEBUG)
+		printf("CR0: 0x%1lx ", cr_ >> 28);
+
+	/* Check FP (vs0) for the expected value. */
+	if (high_vs0 != 0x5555555555555555 || low_vs0 != 0xFFFFFFFFFFFFFFFF) {
+		printf("FP corrupted!");
+			printf("  high = %#16" PRIx64 "  low = %#16" PRIx64 " ",
+				high_vs0, low_vs0);
+		flags.result++;
+	} else
+		printf("FP ok ");
+
+	/* Check VEC (vs32) for the expected value. */
+	if (high_vs32 != 0x5555555555555555 || low_vs32 != 0xFFFFFFFFFFFFFFFF) {
+		printf("VEC corrupted!");
+			printf("  high = %#16" PRIx64 "  low = %#16" PRIx64,
+				high_vs32, low_vs32);
+		flags.result++;
+	} else
+		printf("VEC ok");
+
+	putchar('\n');
+
+	return NULL;
+}
+
+/* Thread to force context switch */
+void *pong(void *not_used)
+{
+	/* Wait thread get its name "pong". */
+	if (DEBUG)
+		sleep(1);
+
+	/* Classed as an interactive-like thread. */
+	while (1)
+		sched_yield();
+}
+
+/* Function that creates a thread and launches the "ping" task. */
+void test_fp_vec(int fp, int vec, pthread_attr_t *attr)
+{
+	int retries = 2;
+	void *ret_value;
+	pthread_t t0;
+
+	flags.touch_fp = fp;
+	flags.touch_vec = vec;
+
+	/*
+	 * Without luck it's possible that the transaction is aborted not due to
+	 * the unavailable exception caught in the middle as we expect but also,
+	 * for instance, due to a context switch or due to a KVM reschedule (if
+	 * it's running on a VM). Thus we try a few times before giving up,
+	 * checking if the failure cause is the one we expect.
+	 */
+	do {
+		/* Bind 'ping' to CPU 0, as specified in 'attr'. */
+		pthread_create(&t0, attr, ping, (void *) &flags);
+		pthread_setname_np(t0, "ping");
+		pthread_join(t0, &ret_value);
+		retries--;
+	} while (ret_value != NULL && retries);
+
+	if (!retries) {
+		flags.result = 1;
+		if (DEBUG)
+			printf("All transactions failed unexpectedly\n");
+
+	}
+}
+
+int main(int argc, char **argv)
+{
+	int exception; /* FP = 0, VEC = 1, VSX = 2 */
+	pthread_t t1;
+	pthread_attr_t attr;
+	cpu_set_t cpuset;
+
+	/* Set only CPU 0 in the mask. Both threads will be bound to CPU 0. */
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+
+	/* Init pthread attribute. */
+	pthread_attr_init(&attr);
+
+	/* Set CPU 0 mask into the pthread attribute. */
+	pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+
+	pthread_create(&t1, &attr /* Bind 'pong' to CPU 0 */, pong, NULL);
+	pthread_setname_np(t1, "pong"); /* Name it for systemtap convenience */
+
+	flags.result = 0;
+
+	for (exception = 0; exception < NUM_EXCEPTIONS; exception++) {
+		printf("Checking if FP/VEC registers are sane after");
+
+		if (exception == FP_UNA_EXCEPTION)
+			printf(" a FP unavailable exception...\n");
+
+		else if (exception == VEC_UNA_EXCEPTION)
+			printf(" a VEC unavailable exception...\n");
+
+		else
+			printf(" a VSX unavailable exception...\n");
+
+		flags.exception = exception;
+
+		test_fp_vec(0, 0, &attr);
+		test_fp_vec(1, 0, &attr);
+		test_fp_vec(0, 1, &attr);
+		test_fp_vec(1, 1, &attr);
+
+	}
+
+	if (flags.result > 0) {
+		printf("result: failed!\n");
+		exit(1);
+	} else {
+		printf("result: success\n");
+		exit(0);
+	}
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index 0ffff04433c5..df4204247d45 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -47,6 +47,11 @@ static inline bool failure_is_syscall(void)
 	return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL;
 }
 
+static inline bool failure_is_unavailable(void)
+{
+	return (failure_code() & TM_CAUSE_FAC_UNAV) == TM_CAUSE_FAC_UNAV;
+}
+
 static inline bool failure_is_nesting(void)
 {
 	return (__builtin_get_texasru() & 0x400000);
-- 
cgit v1.2.3


From d4dbfa4bb4c624636eeef9efc6d87c4b7bf2c611 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Wed, 1 Nov 2017 20:48:17 -0400
Subject: tools/power/cpupower: Add 64 bit library detection

The kernel-tools-lib rpm is installing the library to /usr/lib64, and not
/usr/lib as the cpupower Makefile is doing in the kernel tree.  This
resulted in a conflict between the two libraries.  After looking at how
other tools installed libraries, and looking at the perf code in
tools/perf it looks like installing to /usr/lib64 for 64-bit arches is the
correct thing to do.

Checks with 'ldd cpupower' on SLES, RHEL, Fedora, and Ubuntu result in
the correct binary AFAICT:

[root@testsystem cpupower]# ldd cpupower | grep cpupower
        libcpupower.so.0 => /lib64/libcpupower.so.0 (0x00007f1dab447000)

Commit ac5a181d065d ("cpupower: Add cpuidle parts into library") added a
new cpupower library version.  On Fedora, executing the cpupower binary
then resulted in this error

[root@testsystem cpupower]# ./cpupower monitor
./cpupower: symbol lookup error: ./cpupower: undefined symbol:
get_cpu_topology

64-bit libraries should be installed to /usr/lib64, and other libraries
should be installed to /usr/lib.

This code was taken from the perf Makefile.config which supports /usr/lib
and /usr/lib64.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/power/cpupower/Makefile | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index d6e1c02ddcfe..da205d1fa03c 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -30,6 +30,8 @@ OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
+include ../../scripts/Makefile.arch
+
 # --- CONFIGURATION BEGIN ---
 
 # Set the following to `true' to make a unstripped, unoptimized
@@ -79,7 +81,11 @@ bindir ?=	/usr/bin
 sbindir ?=	/usr/sbin
 mandir ?=	/usr/man
 includedir ?=	/usr/include
+ifeq ($(IS_64_BIT), 1)
+libdir ?=	/usr/lib64
+else
 libdir ?=	/usr/lib
+endif
 localedir ?=	/usr/share/locale
 docdir ?=       /usr/share/doc/packages/cpupower
 confdir ?=      /etc/
-- 
cgit v1.2.3


From 69b6f8a9b7961efd7dcc11ab9b1d5be55ed8a15e Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Wed, 1 Nov 2017 20:48:32 -0400
Subject: tools/power/cpupower: add libcpupower.so.0.0.1 to .gitignore

Commit ac5a181d065d ("cpupower: Add cpuidle parts into library") added
libcpupower.so.0.0.1 which should be hidden from git commands.  This
patch changes the ignore to all libcpupower.so.* .

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/power/cpupower/.gitignore | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/.gitignore b/tools/power/cpupower/.gitignore
index d42073f12609..1f9977cc609c 100644
--- a/tools/power/cpupower/.gitignore
+++ b/tools/power/cpupower/.gitignore
@@ -1,7 +1,6 @@
 .libs
 libcpupower.so
-libcpupower.so.0
-libcpupower.so.0.0.0
+libcpupower.so.*
 build/ccdv
 cpufreq-info
 cpufreq-set
-- 
cgit v1.2.3


From eafb3401faf243f7dca0e23325242cb8c2269ee9 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 7 Nov 2017 15:28:43 -0500
Subject: samples/bpf: add a test for bpf_override_return

This adds a basic test for bpf_override_return to verify it works.  We
override the main function for mounting a btrfs fs so it'll return
-ENOMEM and then make sure that trying to mount a btrfs fs will fail.

Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/Makefile                      |  4 ++++
 samples/bpf/test_override_return.sh       | 15 +++++++++++++++
 samples/bpf/tracex7_kern.c                | 16 ++++++++++++++++
 samples/bpf/tracex7_user.c                | 28 ++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h            |  7 ++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  3 ++-
 6 files changed, 71 insertions(+), 2 deletions(-)
 create mode 100755 samples/bpf/test_override_return.sh
 create mode 100644 samples/bpf/tracex7_kern.c
 create mode 100644 samples/bpf/tracex7_user.c

(limited to 'tools')

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 3b4945c1eab0..87db0f9a4c15 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -15,6 +15,7 @@ hostprogs-y += tracex3
 hostprogs-y += tracex4
 hostprogs-y += tracex5
 hostprogs-y += tracex6
+hostprogs-y += tracex7
 hostprogs-y += test_probe_write_user
 hostprogs-y += trace_output
 hostprogs-y += lathist
@@ -61,6 +62,7 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
 tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
 tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
 tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o
 load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
 test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
 trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
@@ -104,6 +106,7 @@ always += tracex3_kern.o
 always += tracex4_kern.o
 always += tracex5_kern.o
 always += tracex6_kern.o
+always += tracex7_kern.o
 always += sock_flags_kern.o
 always += test_probe_write_user_kern.o
 always += trace_output_kern.o
@@ -158,6 +161,7 @@ HOSTLOADLIBES_tracex3 += -lelf
 HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
 HOSTLOADLIBES_tracex6 += -lelf
+HOSTLOADLIBES_tracex7 += -lelf
 HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
 HOSTLOADLIBES_load_sock_ops += -lelf
 HOSTLOADLIBES_test_probe_write_user += -lelf
diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh
new file mode 100755
index 000000000000..e68b9ee6814b
--- /dev/null
+++ b/samples/bpf/test_override_return.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+rm -f testfile.img
+dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
+DEVICE=$(losetup --show -f testfile.img)
+mkfs.btrfs -f $DEVICE
+mkdir tmpmnt
+./tracex7 $DEVICE
+if [ $? -eq 0 ]
+then
+	echo "SUCCESS!"
+else
+	echo "FAILED!"
+fi
+losetup -d $DEVICE
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c
new file mode 100644
index 000000000000..1ab308a43e0f
--- /dev/null
+++ b/samples/bpf/tracex7_kern.c
@@ -0,0 +1,16 @@
+#include <uapi/linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+SEC("kprobe/open_ctree")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	unsigned long rc = -12;
+
+	bpf_override_return(ctx, rc);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c
new file mode 100644
index 000000000000..8a52ac492e8b
--- /dev/null
+++ b/samples/bpf/tracex7_user.c
@@ -0,0 +1,28 @@
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <unistd.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+int main(int argc, char **argv)
+{
+	FILE *f;
+	char filename[256];
+	char command[256];
+	int ret;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	snprintf(command, 256, "mount %s tmpmnt/", argv[1]);
+	f = popen(command, "r");
+	ret = pclose(f);
+
+	return ret ? 0 : 1;
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e880ae6434ee..adb66f78b674 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -677,6 +677,10 @@ union bpf_attr {
  *     @buf: buf to fill
  *     @buf_size: size of the buf
  *     Return : 0 on success or negative error code
+ *
+ * int bpf_override_return(pt_regs, rc)
+ *	@pt_regs: pointer to struct pt_regs
+ *	@rc: the return value to set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -736,7 +740,8 @@ union bpf_attr {
 	FN(xdp_adjust_meta),		\
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
-	FN(getsockopt),
+	FN(getsockopt),			\
+	FN(override_return),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index fd9a17fa8a8b..33cb00e46c49 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -82,7 +82,8 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
 static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
 				       unsigned int buf_size) =
 	(void *) BPF_FUNC_perf_prog_read_value;
-
+static int (*bpf_override_return)(void *ctx, unsigned long rc) =
+	(void *) BPF_FUNC_override_return;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit v1.2.3


From 1852719658c0f853b5481c9eaed862f1a9355edc Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Wed, 8 Nov 2017 13:55:47 +0900
Subject: tools: bpftool: open pinned object without type check

This was needed for opening any file in bpf-fs without knowing
its object type

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/common.c | 15 +++++++++++++--
 tools/bpf/bpftool/main.h   |  1 +
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index aa7017098b2a..6b3d25d6a782 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -122,9 +122,8 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 	return 0;
 }
 
-int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
+int open_obj_pinned(char *path)
 {
-	enum bpf_obj_type type;
 	int fd;
 
 	fd = bpf_obj_get(path);
@@ -136,6 +135,18 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 		return -1;
 	}
 
+	return fd;
+}
+
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
+{
+	enum bpf_obj_type type;
+	int fd;
+
+	fd = open_obj_pinned(path);
+	if (fd < 0)
+		return -1;
+
 	type = get_fd_type(fd);
 	if (type < 0) {
 		close(fd);
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index ff5ad05b137b..2ff2a361af0d 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -89,6 +89,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv,
 int get_fd_type(int fd);
 const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
+int open_obj_pinned(char *path);
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
 
-- 
cgit v1.2.3


From 4990f1f4610b483a60397ed2768d268df228a551 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Wed, 8 Nov 2017 13:55:48 +0900
Subject: tools: bpftool: show filenames of pinned objects

Added support to show filenames of pinned objects.

For example:

root@test# ./bpftool prog
3: tracepoint  name tracepoint__irq  tag f677a7dd722299a3
    loaded_at Oct 26/11:39  uid 0
    xlated 160B  not jited  memlock 4096B  map_ids 4
    pinned /sys/fs/bpf/softirq_prog

4: tracepoint  name tracepoint__irq  tag ea5dc530d00b92b6
    loaded_at Oct 26/11:39  uid 0
    xlated 392B  not jited  memlock 4096B  map_ids 4,6

root@test# ./bpftool --json --pretty prog
[{
        "id": 3,
        "type": "tracepoint",
        "name": "tracepoint__irq",
        "tag": "f677a7dd722299a3",
        "loaded_at": "Oct 26/11:39",
        "uid": 0,
        "bytes_xlated": 160,
        "jited": false,
        "bytes_memlock": 4096,
        "map_ids": [4
        ],
        "pinned": ["/sys/fs/bpf/softirq_prog"
        ]
    },{
        "id": 4,
        "type": "tracepoint",
        "name": "tracepoint__irq",
        "tag": "ea5dc530d00b92b6",
        "loaded_at": "Oct 26/11:39",
        "uid": 0,
        "bytes_xlated": 392,
        "jited": false,
        "bytes_memlock": 4096,
        "map_ids": [4,6
        ],
        "pinned": []
    }
]

root@test# ./bpftool map
4: hash  name start  flags 0x0
    key 4B  value 16B  max_entries 10240  memlock 1003520B
    pinned /sys/fs/bpf/softirq_map1
5: hash  name iptr  flags 0x0
    key 4B  value 8B  max_entries 10240  memlock 921600B

root@test# ./bpftool --json --pretty map
[{
        "id": 4,
        "type": "hash",
        "name": "start",
        "flags": 0,
        "bytes_key": 4,
        "bytes_value": 16,
        "max_entries": 10240,
        "bytes_memlock": 1003520,
        "pinned": ["/sys/fs/bpf/softirq_map1"
        ]
    },{
        "id": 5,
        "type": "hash",
        "name": "iptr",
        "flags": 0,
        "bytes_key": 4,
        "bytes_value": 8,
        "max_entries": 10240,
        "bytes_memlock": 921600,
        "pinned": []
    }
]

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/common.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/main.c   |  8 +++++
 tools/bpf/bpftool/main.h   | 17 ++++++++++
 tools/bpf/bpftool/map.c    | 21 ++++++++++++
 tools/bpf/bpftool/prog.c   | 24 ++++++++++++++
 5 files changed, 152 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 6b3d25d6a782..2bd3b280e6dd 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -34,7 +34,9 @@
 /* Author: Jakub Kicinski <kubakici@wp.pl> */
 
 #include <errno.h>
+#include <fts.h>
 #include <libgen.h>
+#include <mntent.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -321,3 +323,83 @@ void print_hex_data_json(uint8_t *data, size_t len)
 		jsonw_printf(json_wtr, "\"0x%02hhx\"", data[i]);
 	jsonw_end_array(json_wtr);
 }
+
+int build_pinned_obj_table(struct pinned_obj_table *tab,
+			   enum bpf_obj_type type)
+{
+	struct bpf_prog_info pinned_info = {};
+	struct pinned_obj *obj_node = NULL;
+	__u32 len = sizeof(pinned_info);
+	struct mntent *mntent = NULL;
+	enum bpf_obj_type objtype;
+	FILE *mntfile = NULL;
+	FTSENT *ftse = NULL;
+	FTS *fts = NULL;
+	int fd, err;
+
+	mntfile = setmntent("/proc/mounts", "r");
+	if (!mntfile)
+		return -1;
+
+	while ((mntent = getmntent(mntfile))) {
+		char *path[] = { mntent->mnt_dir, NULL };
+
+		if (strncmp(mntent->mnt_type, "bpf", 3) != 0)
+			continue;
+
+		fts = fts_open(path, 0, NULL);
+		if (!fts)
+			continue;
+
+		while ((ftse = fts_read(fts))) {
+			if (!(ftse->fts_info & FTS_F))
+				continue;
+			fd = open_obj_pinned(ftse->fts_path);
+			if (fd < 0)
+				continue;
+
+			objtype = get_fd_type(fd);
+			if (objtype != type) {
+				close(fd);
+				continue;
+			}
+			memset(&pinned_info, 0, sizeof(pinned_info));
+			err = bpf_obj_get_info_by_fd(fd, &pinned_info, &len);
+			if (err) {
+				close(fd);
+				continue;
+			}
+
+			obj_node = malloc(sizeof(*obj_node));
+			if (!obj_node) {
+				close(fd);
+				fts_close(fts);
+				fclose(mntfile);
+				return -1;
+			}
+
+			memset(obj_node, 0, sizeof(*obj_node));
+			obj_node->id = pinned_info.id;
+			obj_node->path = strdup(ftse->fts_path);
+			hash_add(tab->table, &obj_node->hash, obj_node->id);
+
+			close(fd);
+		}
+		fts_close(fts);
+	}
+	fclose(mntfile);
+	return 0;
+}
+
+void delete_pinned_obj_table(struct pinned_obj_table *tab)
+{
+	struct pinned_obj *obj;
+	struct hlist_node *tmp;
+	unsigned int bkt;
+
+	hash_for_each_safe(tab->table, bkt, tmp, obj, hash) {
+		hash_del(&obj->hash);
+		free(obj->path);
+		free(obj);
+	}
+}
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 78d9afb74ef4..6ad53f1797fa 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -54,6 +54,8 @@ static int (*last_do_help)(int argc, char **argv);
 json_writer_t *json_wtr;
 bool pretty_output;
 bool json_output;
+struct pinned_obj_table prog_table;
+struct pinned_obj_table map_table;
 
 void usage(void)
 {
@@ -272,6 +274,9 @@ int main(int argc, char **argv)
 	json_output = false;
 	bin_name = argv[0];
 
+	hash_init(prog_table.table);
+	hash_init(map_table.table);
+
 	while ((opt = getopt_long(argc, argv, "Vhpj",
 				  options, NULL)) >= 0) {
 		switch (opt) {
@@ -311,5 +316,8 @@ int main(int argc, char **argv)
 	if (json_output)
 		jsonw_destroy(&json_wtr);
 
+	delete_pinned_obj_table(&prog_table);
+	delete_pinned_obj_table(&map_table);
+
 	return ret;
 }
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 2ff2a361af0d..13453de2e570 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -42,6 +42,7 @@
 #include <stdio.h>
 #include <linux/bpf.h>
 #include <linux/kernel.h>
+#include <linux/hashtable.h>
 
 #include "json_writer.h"
 
@@ -70,6 +71,8 @@ extern const char *bin_name;
 
 extern json_writer_t *json_wtr;
 extern bool json_output;
+extern struct pinned_obj_table prog_table;
+extern struct pinned_obj_table map_table;
 
 void p_err(const char *fmt, ...);
 void p_info(const char *fmt, ...);
@@ -78,6 +81,20 @@ bool is_prefix(const char *pfx, const char *str);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __attribute__((noreturn));
 
+struct pinned_obj_table {
+	DECLARE_HASHTABLE(table, 16);
+};
+
+struct pinned_obj {
+	__u32 id;
+	char *path;
+	struct hlist_node hash;
+};
+
+int build_pinned_obj_table(struct pinned_obj_table *table,
+			   enum bpf_obj_type type);
+void delete_pinned_obj_table(struct pinned_obj_table *tab);
+
 struct cmd {
 	const char *cmd;
 	int (*func)(int argc, char **argv);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e978ab23a77f..de0980657cef 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -436,6 +436,18 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
 	free(memlock);
 
+	if (!hash_empty(map_table.table)) {
+		struct pinned_obj *obj;
+
+		jsonw_name(json_wtr, "pinned");
+		jsonw_start_array(json_wtr);
+		hash_for_each_possible(map_table.table, obj, hash, info->id) {
+			if (obj->id == info->id)
+				jsonw_string(json_wtr, obj->path);
+		}
+		jsonw_end_array(json_wtr);
+	}
+
 	jsonw_end_object(json_wtr);
 
 	return 0;
@@ -466,7 +478,14 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	free(memlock);
 
 	printf("\n");
+	if (!hash_empty(map_table.table)) {
+		struct pinned_obj *obj;
 
+		hash_for_each_possible(map_table.table, obj, hash, info->id) {
+			if (obj->id == info->id)
+				printf("\tpinned %s\n", obj->path);
+		}
+	}
 	return 0;
 }
 
@@ -478,6 +497,8 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
+	build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
+
 	if (argc == 2) {
 		fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
 		if (fd < 0)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d3ab808dc882..8f94b8ac2e63 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -272,6 +272,18 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
+	if (!hash_empty(prog_table.table)) {
+		struct pinned_obj *obj;
+
+		jsonw_name(json_wtr, "pinned");
+		jsonw_start_array(json_wtr);
+		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
+			if (obj->id == info->id)
+				jsonw_string(json_wtr, obj->path);
+		}
+		jsonw_end_array(json_wtr);
+	}
+
 	jsonw_end_object(json_wtr);
 }
 
@@ -331,6 +343,16 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
+	if (!hash_empty(prog_table.table)) {
+		struct pinned_obj *obj;
+
+		printf("\n");
+		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
+			if (obj->id == info->id)
+				printf("\tpinned %s\n", obj->path);
+		}
+	}
+
 	printf("\n");
 }
 
@@ -360,6 +382,8 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
+	build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+
 	if (argc == 2) {
 		fd = prog_parse_fd(&argc, &argv);
 		if (fd < 0)
-- 
cgit v1.2.3


From c541b73466549c4aa4ee20ccd04ba52e4c95d6eb Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Wed, 8 Nov 2017 13:55:49 +0900
Subject: tools: bpftool: optionally show filenames of pinned objects

Making it optional to show file names of pinned objects because
it scans complete bpf-fs filesystem which is costly.
Added option -f|--bpffs. Documentation updated.

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst  |  5 ++++-
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  5 ++++-
 tools/bpf/bpftool/main.c                         | 14 +++++++++++---
 tools/bpf/bpftool/main.h                         |  3 ++-
 tools/bpf/bpftool/map.c                          |  3 ++-
 tools/bpf/bpftool/prog.c                         |  3 ++-
 6 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index abb9ee940b15..9f51a268eb06 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -12,7 +12,7 @@ SYNOPSIS
 
 	**bpftool** [*OPTIONS*] **map** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
 	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
@@ -86,6 +86,9 @@ OPTIONS
 	-p, --pretty
 		  Generate human-readable JSON output. Implies **-j**.
 
+	-f, --bpffs
+		  Show file names of pinned maps.
+
 EXAMPLES
 ========
 **# bpftool map show**
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 0f25d3c39e05..36e8d1c3c40d 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -12,7 +12,7 @@ SYNOPSIS
 
 	**bpftool** [*OPTIONS*] **prog** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
 	{ **show** | **dump xlated** | **dump jited** | **pin** | **help** }
@@ -75,6 +75,9 @@ OPTIONS
 	-p, --pretty
 		  Generate human-readable JSON output. Implies **-j**.
 
+	-f, --bpffs
+		  Show file names of pinned programs.
+
 EXAMPLES
 ========
 **# bpftool prog show**
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 6ad53f1797fa..d6e4762170a4 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -54,6 +54,7 @@ static int (*last_do_help)(int argc, char **argv);
 json_writer_t *json_wtr;
 bool pretty_output;
 bool json_output;
+bool show_pinned;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
 
@@ -265,6 +266,7 @@ int main(int argc, char **argv)
 		{ "help",	no_argument,	NULL,	'h' },
 		{ "pretty",	no_argument,	NULL,	'p' },
 		{ "version",	no_argument,	NULL,	'V' },
+		{ "bpffs",	no_argument,	NULL,	'f' },
 		{ 0 }
 	};
 	int opt, ret;
@@ -272,12 +274,13 @@ int main(int argc, char **argv)
 	last_do_help = do_help;
 	pretty_output = false;
 	json_output = false;
+	show_pinned = false;
 	bin_name = argv[0];
 
 	hash_init(prog_table.table);
 	hash_init(map_table.table);
 
-	while ((opt = getopt_long(argc, argv, "Vhpj",
+	while ((opt = getopt_long(argc, argv, "Vhpjf",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -290,6 +293,9 @@ int main(int argc, char **argv)
 		case 'j':
 			json_output = true;
 			break;
+		case 'f':
+			show_pinned = true;
+			break;
 		default:
 			usage();
 		}
@@ -316,8 +322,10 @@ int main(int argc, char **argv)
 	if (json_output)
 		jsonw_destroy(&json_wtr);
 
-	delete_pinned_obj_table(&prog_table);
-	delete_pinned_obj_table(&map_table);
+	if (show_pinned) {
+		delete_pinned_obj_table(&prog_table);
+		delete_pinned_obj_table(&map_table);
+	}
 
 	return ret;
 }
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 13453de2e570..9c191e222d6f 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -59,7 +59,7 @@
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS						\
-	"OPTIONS := { {-j|--json} [{-p|--pretty}] }"
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
 
 enum bpf_obj_type {
 	BPF_OBJ_UNKNOWN,
@@ -71,6 +71,7 @@ extern const char *bin_name;
 
 extern json_writer_t *json_wtr;
 extern bool json_output;
+extern bool show_pinned;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
 
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index de0980657cef..e2450c8e88e6 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -497,7 +497,8 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
+	if (show_pinned)
+		build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
 
 	if (argc == 2) {
 		fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 8f94b8ac2e63..f45c44ef9bec 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -382,7 +382,8 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+	if (show_pinned)
+		build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
 
 	if (argc == 2) {
 		fd = prog_parse_fd(&argc, &argv);
-- 
cgit v1.2.3


From f3edacbd697f94a743fff1a3d26910ab99948ba7 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 11 Nov 2017 18:24:55 +0900
Subject: bpf: Revert bpf_overrid_function() helper changes.

NACK'd by x86 maintainer.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/Kconfig                              |  3 ---
 arch/x86/Kconfig                          |  1 -
 arch/x86/include/asm/kprobes.h            |  4 ----
 arch/x86/include/asm/ptrace.h             |  5 ----
 arch/x86/kernel/kprobes/ftrace.c          | 14 -----------
 include/linux/filter.h                    |  3 +--
 include/linux/trace_events.h              |  1 -
 include/uapi/linux/bpf.h                  |  7 +-----
 kernel/bpf/core.c                         |  3 ---
 kernel/bpf/verifier.c                     |  2 --
 kernel/events/core.c                      |  7 ------
 kernel/trace/Kconfig                      | 11 ---------
 kernel/trace/bpf_trace.c                  | 35 ---------------------------
 kernel/trace/trace_kprobe.c               | 40 ++++++-------------------------
 kernel/trace/trace_probe.h                |  6 -----
 samples/bpf/Makefile                      |  4 ----
 samples/bpf/test_override_return.sh       | 15 ------------
 samples/bpf/tracex7_kern.c                | 16 -------------
 samples/bpf/tracex7_user.c                | 28 ----------------------
 tools/include/uapi/linux/bpf.h            |  7 +-----
 tools/testing/selftests/bpf/bpf_helpers.h |  3 +--
 21 files changed, 11 insertions(+), 204 deletions(-)
 delete mode 100755 samples/bpf/test_override_return.sh
 delete mode 100644 samples/bpf/tracex7_kern.c
 delete mode 100644 samples/bpf/tracex7_user.c

(limited to 'tools')

diff --git a/arch/Kconfig b/arch/Kconfig
index 6e8520f09bc1..057370a0ac4e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -196,9 +196,6 @@ config HAVE_OPTPROBES
 config HAVE_KPROBES_ON_FTRACE
 	bool
 
-config HAVE_KPROBE_OVERRIDE
-	bool
-
 config HAVE_NMI
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 51458c1a0b4a..2fdb23313dd5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -153,7 +153,6 @@ config X86
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
-	select HAVE_KPROBE_OVERRIDE
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH			if X86_64
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index c6c3b1f4306a..6cf65437b5e5 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -67,10 +67,6 @@ extern const int kretprobe_blacklist_size;
 void arch_remove_kprobe(struct kprobe *p);
 asmlinkage void kretprobe_trampoline(void);
 
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs);
-#endif
-
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 2370bb0149cc..c0e3c45cf6ab 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -109,11 +109,6 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->ax;
 }
 
-static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
-{
-	regs->ax = rc;
-}
-
 /*
  * user_mode(regs) determines whether a register set came from user
  * mode.  On x86_32, this is true if V8086 mode was enabled OR if the
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 3c455bf490cb..041f7b6dfa0f 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -97,17 +97,3 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p)
 	p->ainsn.boostable = false;
 	return 0;
 }
-
-asmlinkage void override_func(void);
-asm(
-	".type override_func, @function\n"
-	"override_func:\n"
-	"	ret\n"
-	".size override_func, .-override_func\n"
-);
-
-void arch_ftrace_kprobe_override_function(struct pt_regs *regs)
-{
-	regs->ip = (unsigned long)&override_func;
-}
-NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index eaec066f99e8..0cd02ff4ae30 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -459,8 +459,7 @@ struct bpf_prog {
 				locked:1,	/* Program image locked? */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
-				dst_needed:1,	/* Do we need dst entry? */
-				kprobe_override:1; /* Do we override a kprobe? */
+				dst_needed:1;	/* Do we need dst entry? */
 	kmemcheck_bitfield_end(meta);
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	u32			len;		/* Number of filter blocks */
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 17e5e820a84c..84014ecfa67f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -523,7 +523,6 @@ do {									\
 struct perf_event;
 
 DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
-DECLARE_PER_CPU(int, bpf_kprobe_override);
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index adb66f78b674..e880ae6434ee 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -677,10 +677,6 @@ union bpf_attr {
  *     @buf: buf to fill
  *     @buf_size: size of the buf
  *     Return : 0 on success or negative error code
- *
- * int bpf_override_return(pt_regs, rc)
- *	@pt_regs: pointer to struct pt_regs
- *	@rc: the return value to set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -740,8 +736,7 @@ union bpf_attr {
 	FN(xdp_adjust_meta),		\
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
-	FN(getsockopt),			\
-	FN(override_return),
+	FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 271daad31f37..8a6c37762330 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1326,9 +1326,6 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)
 {
-	if (fp->kprobe_override)
-		return false;
-
 	if (!array->owner_prog_type) {
 		/* There's no owner yet where we could check for
 		 * compatibility.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bc464b8ec91e..4a942e2e753d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4357,8 +4357,6 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			prog->dst_needed = 1;
 		if (insn->imm == BPF_FUNC_get_prandom_u32)
 			bpf_user_rnd_init_once();
-		if (insn->imm == BPF_FUNC_override_return)
-			prog->kprobe_override = 1;
 		if (insn->imm == BPF_FUNC_tail_call) {
 			/* If we tail call into other programs, we
 			 * cannot make any assumptions since they can
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ac240d31b5bf..42d24bd64ea4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8171,13 +8171,6 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 		return -EINVAL;
 	}
 
-	/* Kprobe override only works for kprobes, not uprobes. */
-	if (prog->kprobe_override &&
-	    !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) {
-		bpf_prog_put(prog);
-		return -EINVAL;
-	}
-
 	if (is_tracepoint || is_syscall_tp) {
 		int off = trace_event_get_offsets(event->tp_event);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 9dc0deeaad2b..434c840e2d82 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -518,17 +518,6 @@ config FUNCTION_PROFILER
 
 	  If in doubt, say N.
 
-config BPF_KPROBE_OVERRIDE
-	bool "Enable BPF programs to override a kprobed function"
-	depends on BPF_EVENTS
-	depends on KPROBES_ON_FTRACE
-	depends on HAVE_KPROBE_OVERRIDE
-	depends on DYNAMIC_FTRACE_WITH_REGS
-	default n
-	help
-	 Allows BPF to override the execution of a probed function and
-	 set a different return value.  This is used for error injection.
-
 config FTRACE_MCOUNT_RECORD
 	def_bool y
 	depends on DYNAMIC_FTRACE
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1865b0d4cdeb..506efe6e8ed9 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -13,10 +13,6 @@
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
-#include <linux/kprobes.h>
-#include <asm/kprobes.h>
-
-#include "trace_probe.h"
 #include "trace.h"
 
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
@@ -80,29 +76,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 }
 EXPORT_SYMBOL_GPL(trace_call_bpf);
 
-#ifdef CONFIG_BPF_KPROBE_OVERRIDE
-BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
-{
-	__this_cpu_write(bpf_kprobe_override, 1);
-	regs_set_return_value(regs, rc);
-	arch_ftrace_kprobe_override_function(regs);
-	return 0;
-}
-#else
-BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
-{
-	return -EINVAL;
-}
-#endif
-
-static const struct bpf_func_proto bpf_override_return_proto = {
-	.func		= bpf_override_return,
-	.gpl_only	= true,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_ANYTHING,
-};
-
 BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
 {
 	int ret;
@@ -578,10 +551,6 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_perf_event_read_value:
 		return &bpf_perf_event_read_value_proto;
-	case BPF_FUNC_override_return:
-		pr_warn_ratelimited("%s[%d] is installing a program with bpf_override_return helper that may cause unexpected behavior!",
-				    current->comm, task_pid_nr(current));
-		return &bpf_override_return_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -797,10 +766,6 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
 	struct bpf_prog_array *new_array;
 	int ret = -EEXIST;
 
-	/* Kprobe override only works for ftrace based kprobes. */
-	if (prog->kprobe_override && !trace_kprobe_ftrace(event->tp_event))
-		return -EINVAL;
-
 	mutex_lock(&bpf_event_mutex);
 
 	if (event->prog)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8e3c9ec1faf7..abf92e478cfb 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -42,7 +42,6 @@ struct trace_kprobe {
 	(offsetof(struct trace_kprobe, tp.args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
-DEFINE_PER_CPU(int, bpf_kprobe_override);
 
 static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
 {
@@ -88,12 +87,6 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
 	return nhit;
 }
 
-int trace_kprobe_ftrace(struct trace_event_call *call)
-{
-	struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
-	return kprobe_ftrace(&tk->rp.kp);
-}
-
 static int register_kprobe_event(struct trace_kprobe *tk);
 static int unregister_kprobe_event(struct trace_kprobe *tk);
 
@@ -1177,7 +1170,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call)
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
-static int
+static void
 kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct trace_event_call *call = &tk->tp.call;
@@ -1186,29 +1179,12 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	int size, __size, dsize;
 	int rctx;
 
-	if (bpf_prog_array_valid(call)) {
-		int ret;
-
-		ret = trace_call_bpf(call, regs);
-
-		/*
-		 * We need to check and see if we modified the pc of the
-		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the instruction skipping.  Also reset our state so
-		 * we are clean the next pass through.
-		 */
-		if (__this_cpu_read(bpf_kprobe_override)) {
-			__this_cpu_write(bpf_kprobe_override, 0);
-			reset_current_kprobe();
-			return 1;
-		}
-		if (!ret)
-			return 0;
-	}
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
+		return;
 
 	head = this_cpu_ptr(call->perf_events);
 	if (hlist_empty(head))
-		return 0;
+		return;
 
 	dsize = __get_data_size(&tk->tp, regs);
 	__size = sizeof(*entry) + tk->tp.size + dsize;
@@ -1217,14 +1193,13 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 	entry = perf_trace_buf_alloc(size, NULL, &rctx);
 	if (!entry)
-		return 0;
+		return;
 
 	entry->ip = (unsigned long)tk->rp.kp.addr;
 	memset(&entry[1], 0, dsize);
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL, NULL);
-	return 0;
 }
 NOKPROBE_SYMBOL(kprobe_perf_func);
 
@@ -1300,7 +1275,6 @@ static int kprobe_register(struct trace_event_call *event,
 static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
-	int ret = 0;
 
 	raw_cpu_inc(*tk->nhit);
 
@@ -1308,9 +1282,9 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
 	if (tk->tp.flags & TP_FLAG_PROFILE)
-		ret = kprobe_perf_func(tk, regs);
+		kprobe_perf_func(tk, regs);
 #endif
-	return ret;
+	return 0;	/* We don't tweek kernel, so just return 0 */
 }
 NOKPROBE_SYMBOL(kprobe_dispatcher);
 
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index adbb3f7d1fb5..903273c93e61 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -253,7 +253,6 @@ struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
 struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
-int trace_kprobe_ftrace(struct trace_event_call *call);
 #else
 /* uprobes do not support symbol fetch methods */
 #define fetch_symbol_u8			NULL
@@ -279,11 +278,6 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
-
-static inline int trace_kprobe_ftrace(struct trace_event_call *call)
-{
-	return 0;
-}
 #endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 87db0f9a4c15..3b4945c1eab0 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -15,7 +15,6 @@ hostprogs-y += tracex3
 hostprogs-y += tracex4
 hostprogs-y += tracex5
 hostprogs-y += tracex6
-hostprogs-y += tracex7
 hostprogs-y += test_probe_write_user
 hostprogs-y += trace_output
 hostprogs-y += lathist
@@ -62,7 +61,6 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
 tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
 tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
 tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
-tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o
 load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
 test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
 trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
@@ -106,7 +104,6 @@ always += tracex3_kern.o
 always += tracex4_kern.o
 always += tracex5_kern.o
 always += tracex6_kern.o
-always += tracex7_kern.o
 always += sock_flags_kern.o
 always += test_probe_write_user_kern.o
 always += trace_output_kern.o
@@ -161,7 +158,6 @@ HOSTLOADLIBES_tracex3 += -lelf
 HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
 HOSTLOADLIBES_tracex6 += -lelf
-HOSTLOADLIBES_tracex7 += -lelf
 HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
 HOSTLOADLIBES_load_sock_ops += -lelf
 HOSTLOADLIBES_test_probe_write_user += -lelf
diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh
deleted file mode 100755
index e68b9ee6814b..000000000000
--- a/samples/bpf/test_override_return.sh
+++ /dev/null
@@ -1,15 +0,0 @@
-#!/bin/bash
-
-rm -f testfile.img
-dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
-DEVICE=$(losetup --show -f testfile.img)
-mkfs.btrfs -f $DEVICE
-mkdir tmpmnt
-./tracex7 $DEVICE
-if [ $? -eq 0 ]
-then
-	echo "SUCCESS!"
-else
-	echo "FAILED!"
-fi
-losetup -d $DEVICE
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c
deleted file mode 100644
index 1ab308a43e0f..000000000000
--- a/samples/bpf/tracex7_kern.c
+++ /dev/null
@@ -1,16 +0,0 @@
-#include <uapi/linux/ptrace.h>
-#include <uapi/linux/bpf.h>
-#include <linux/version.h>
-#include "bpf_helpers.h"
-
-SEC("kprobe/open_ctree")
-int bpf_prog1(struct pt_regs *ctx)
-{
-	unsigned long rc = -12;
-
-	bpf_override_return(ctx, rc);
-	return 0;
-}
-
-char _license[] SEC("license") = "GPL";
-u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c
deleted file mode 100644
index 8a52ac492e8b..000000000000
--- a/samples/bpf/tracex7_user.c
+++ /dev/null
@@ -1,28 +0,0 @@
-#define _GNU_SOURCE
-
-#include <stdio.h>
-#include <linux/bpf.h>
-#include <unistd.h>
-#include "libbpf.h"
-#include "bpf_load.h"
-
-int main(int argc, char **argv)
-{
-	FILE *f;
-	char filename[256];
-	char command[256];
-	int ret;
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
-	if (load_bpf_file(filename)) {
-		printf("%s", bpf_log_buf);
-		return 1;
-	}
-
-	snprintf(command, 256, "mount %s tmpmnt/", argv[1]);
-	f = popen(command, "r");
-	ret = pclose(f);
-
-	return ret ? 0 : 1;
-}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index adb66f78b674..e880ae6434ee 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -677,10 +677,6 @@ union bpf_attr {
  *     @buf: buf to fill
  *     @buf_size: size of the buf
  *     Return : 0 on success or negative error code
- *
- * int bpf_override_return(pt_regs, rc)
- *	@pt_regs: pointer to struct pt_regs
- *	@rc: the return value to set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -740,8 +736,7 @@ union bpf_attr {
 	FN(xdp_adjust_meta),		\
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
-	FN(getsockopt),			\
-	FN(override_return),
+	FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 33cb00e46c49..fd9a17fa8a8b 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -82,8 +82,7 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
 static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
 				       unsigned int buf_size) =
 	(void *) BPF_FUNC_perf_prog_read_value;
-static int (*bpf_override_return)(void *ctx, unsigned long rc) =
-	(void *) BPF_FUNC_override_return;
+
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit v1.2.3


From fb2a1748355161e050e9f49f1ea9a0ae707a148b Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Sun, 12 Nov 2017 14:54:23 -0800
Subject: tools/testing/nvdimm: unit test clear-error commands

Validate command parsing in acpi_nfit_ctl for the clear error command.
This tests for a crash condition introduced by commit 4b27db7e26cd
"acpi, nfit: add support for the _LSI, _LSR, and _LSW label methods".

Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index edab68c2e221..7217b2b953b5 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1812,6 +1812,7 @@ static int nfit_ctl_test(struct device *dev)
 	unsigned long mask, cmd_size, offset;
 	union {
 		struct nd_cmd_get_config_size cfg_size;
+		struct nd_cmd_clear_error clear_err;
 		struct nd_cmd_ars_status ars_stat;
 		struct nd_cmd_ars_cap ars_cap;
 		char buf[sizeof(struct nd_cmd_ars_status)
@@ -1995,6 +1996,23 @@ static int nfit_ctl_test(struct device *dev)
 		return -EIO;
 	}
 
+	/* test clear error */
+	cmd_size = sizeof(cmds.clear_err);
+	cmds.clear_err = (struct nd_cmd_clear_error) {
+		.length = 512,
+		.cleared = 512,
+	};
+	rc = setup_result(cmds.buf, cmd_size);
+	if (rc)
+		return rc;
+	rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_CLEAR_ERROR,
+			cmds.buf, cmd_size, &cmd_rc);
+	if (rc < 0 || cmd_rc) {
+		dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n",
+				__func__, __LINE__, rc, cmd_rc);
+		return -EIO;
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From a356d2ae50790f49858ebed35da9e206336fafee Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Tue, 14 Nov 2017 07:24:22 +0100
Subject: tools/headers: Sync objtool UAPI header

objtool grew this new warning:

  Warning: synced file at 'tools/objtool/arch/x86/include/asm/inat.h' differs from latest kernel version at 'arch/x86/include/asm/inat.h'

which upstream header grew new INAT_SEG_* definitions.

Sync up the tooling version of the header.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/objtool/arch/x86/include/asm/inat.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'tools')

diff --git a/tools/objtool/arch/x86/include/asm/inat.h b/tools/objtool/arch/x86/include/asm/inat.h
index 02aff0867211..1c78580e58be 100644
--- a/tools/objtool/arch/x86/include/asm/inat.h
+++ b/tools/objtool/arch/x86/include/asm/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE	0
+#define INAT_SEG_REG_DEFAULT	1
+#define INAT_SEG_REG_CS		2
+#define INAT_SEG_REG_SS		3
+#define INAT_SEG_REG_DS		4
+#define INAT_SEG_REG_ES		5
+#define INAT_SEG_REG_FS		6
+#define INAT_SEG_REG_GS		7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
-- 
cgit v1.2.3


From b6ff63911232c2823e2763371ec4462ac64cc331 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sun, 12 Nov 2017 14:49:11 -0800
Subject: bpf: fix and add test cases for ARG_CONST_SIZE_OR_ZERO semantics
 change

Fix a few test cases to allow non-NULL map/packet/stack pointer
with size = 0. Change a few tests using bpf_probe_read to use
bpf_probe_write_user so ARG_CONST_SIZE arg can still be properly
tested. One existing test case already covers size = 0 with non-NULL
packet pointer, so add additional tests so all cases of
size = 0 and 0 <= size <= legal_upper_bound with non-NULL
map/packet/stack pointer are covered.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 131 ++++++++++++++++++++++++----
 1 file changed, 112 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index bb3c4ad8c59f..bf092b83e453 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3579,7 +3579,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to packet: test19, cls helper fail range zero",
+		"helper access to packet: test19, cls helper range zero",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
 				    offsetof(struct __sk_buff, data)),
@@ -3599,8 +3599,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.result = REJECT,
-		.errstr = "invalid access to packet",
+		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
@@ -4379,10 +4378,10 @@ static struct bpf_test tests[] = {
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
@@ -4486,9 +4485,10 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
 				offsetof(struct test_val, foo)),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
@@ -4622,13 +4622,14 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
-		.errstr = "R1 min value is outside of the array range",
+		.errstr = "R2 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -4765,13 +4766,14 @@ static struct bpf_test tests[] = {
 			BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
 				offsetof(struct test_val, foo), 4),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
-		.errstr = "R1 min value is outside of the array range",
+		.errstr = "R2 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5350,7 +5352,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid stack type R1 off=-64 access_size=0",
+		.errstr = "invalid indirect read from stack off -64+0 size 64",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5505,7 +5507,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid stack type R1 off=-64 access_size=0",
+		.errstr = "invalid indirect read from stack off -64+0 size 64",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5668,7 +5670,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size = 0 not allowed on != NULL",
+		"helper access to variable memory: size = 0 allowed on != NULL stack pointer",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
@@ -5681,8 +5683,99 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid stack type R1 off=-8 access_size=0",
-		.result = REJECT,
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size = 0 allowed on != NULL map pointer",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL map pointer",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL packet pointer",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_6),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-- 
cgit v1.2.3


From e7d65f9c8b88795c5fa897cf9e6d6d166d635724 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Fri, 13 Oct 2017 11:27:10 -0600
Subject: selftests: timers: Update .gitignore with newly added tests

Update .gitignore with newly added tests.

Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/timers/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore
index cc986621f512..2c8ac8416299 100644
--- a/tools/testing/selftests/timers/.gitignore
+++ b/tools/testing/selftests/timers/.gitignore
@@ -18,3 +18,5 @@ threadtest
 valid-adjtimex
 adjtick
 set-tz
+freq-step
+rtctest_setdate
-- 
cgit v1.2.3


From b5b657acc4eefed47cd19ca2ff2ab73641fb6d14 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Fri, 13 Oct 2017 11:28:40 -0600
Subject: selftests: vm: Update .gitignore with newly added tests

Update .gitignore with newly added tests.

Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/vm/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 142c565bb351..1ca2ee4d15b9 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -8,3 +8,5 @@ on-fault-limit
 transhuge-stress
 userfaultfd
 mlock-intersect-test
+mlock-random-test
+virtual_address_range
-- 
cgit v1.2.3


From d54e9a8f4430d789a7b462b5318b1012d5643fd4 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Fri, 13 Oct 2017 11:06:29 -0600
Subject: selftests: seccomp: update .gitignore with newly added tests

Update .gitignore with newly added tests.

Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/seccomp/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/seccomp/.gitignore b/tools/testing/selftests/seccomp/.gitignore
index 346d83ca8069..5af29d3a1b0a 100644
--- a/tools/testing/selftests/seccomp/.gitignore
+++ b/tools/testing/selftests/seccomp/.gitignore
@@ -1 +1,2 @@
 seccomp_bpf
+seccomp_benchmark
-- 
cgit v1.2.3


From 2d80c92d6cae986e8f3f04e64dbea9883680ae1c Mon Sep 17 00:00:00 2001
From: Steve Muckle <smuckle.linux@gmail.com>
Date: Thu, 12 Oct 2017 21:44:57 -0700
Subject: selftests/exec: include cwd in long path calculation

When creating a pathname close to PATH_MAX to test execveat, factor in
the current working directory path otherwise we end up with an absolute
path that is longer than PATH_MAX. While execveat() may succeed, subsequent
calls to the kernel from the runtime environment which are required to
successfully execute the test binary/script may fail because of this.

To keep the semantics of the test the same, rework the relative pathname
part of the test to be relative to the root directory so it isn't
decreased by the length of the current working directory path.

Signed-off-by: Steve Muckle <smuckle.linux@gmail.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/exec/execveat.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index 8d5d1d2ee7c1..67cd4597db2b 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -147,7 +147,7 @@ static void exe_cp(const char *src, const char *dest)
 }
 
 #define XX_DIR_LEN 200
-static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
+static int check_execveat_pathmax(int root_dfd, const char *src, int is_script)
 {
 	int fail = 0;
 	int ii, count, len;
@@ -156,20 +156,30 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
 
 	if (*longpath == '\0') {
 		/* Create a filename close to PATH_MAX in length */
+		char *cwd = getcwd(NULL, 0);
+
+		if (!cwd) {
+			printf("Failed to getcwd(), errno=%d (%s)\n",
+			       errno, strerror(errno));
+			return 2;
+		}
+		strcpy(longpath, cwd);
+		strcat(longpath, "/");
 		memset(longname, 'x', XX_DIR_LEN - 1);
 		longname[XX_DIR_LEN - 1] = '/';
 		longname[XX_DIR_LEN] = '\0';
-		count = (PATH_MAX - 3) / XX_DIR_LEN;
+		count = (PATH_MAX - 3 - strlen(cwd)) / XX_DIR_LEN;
 		for (ii = 0; ii < count; ii++) {
 			strcat(longpath, longname);
 			mkdir(longpath, 0755);
 		}
-		len = (PATH_MAX - 3) - (count * XX_DIR_LEN);
+		len = (PATH_MAX - 3 - strlen(cwd)) - (count * XX_DIR_LEN);
 		if (len <= 0)
 			len = 1;
 		memset(longname, 'y', len);
 		longname[len] = '\0';
 		strcat(longpath, longname);
+		free(cwd);
 	}
 	exe_cp(src, longpath);
 
@@ -190,7 +200,7 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
 	}
 
 	/*
-	 * Execute as a long pathname relative to ".".  If this is a script,
+	 * Execute as a long pathname relative to "/".  If this is a script,
 	 * the interpreter will launch but fail to open the script because its
 	 * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX.
 	 *
@@ -200,10 +210,10 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
 	 * the exit status shall be 126."), so allow either.
 	 */
 	if (is_script)
-		fail += check_execveat_invoked_rc(dot_dfd, longpath, 0,
+		fail += check_execveat_invoked_rc(root_dfd, longpath + 1, 0,
 						  127, 126);
 	else
-		fail += check_execveat(dot_dfd, longpath, 0);
+		fail += check_execveat(root_dfd, longpath + 1, 0);
 
 	return fail;
 }
@@ -218,6 +228,7 @@ static int run_tests(void)
 	int subdir_dfd_ephemeral = open_or_die("subdir.ephemeral",
 					       O_DIRECTORY|O_RDONLY);
 	int dot_dfd = open_or_die(".", O_DIRECTORY|O_RDONLY);
+	int root_dfd = open_or_die("/", O_DIRECTORY|O_RDONLY);
 	int dot_dfd_path = open_or_die(".", O_DIRECTORY|O_RDONLY|O_PATH);
 	int dot_dfd_cloexec = open_or_die(".", O_DIRECTORY|O_RDONLY|O_CLOEXEC);
 	int fd = open_or_die("execveat", O_RDONLY);
@@ -353,8 +364,8 @@ static int run_tests(void)
 	/* Attempt to execute relative to non-directory => ENOTDIR */
 	fail += check_execveat_fail(fd, "execveat", 0, ENOTDIR);
 
-	fail += check_execveat_pathmax(dot_dfd, "execveat", 0);
-	fail += check_execveat_pathmax(dot_dfd, "script", 1);
+	fail += check_execveat_pathmax(root_dfd, "execveat", 0);
+	fail += check_execveat_pathmax(root_dfd, "script", 1);
 	return fail;
 }
 
-- 
cgit v1.2.3


From d3611d72070591b4255cdccf1bc0cc4f0e56b1a0 Mon Sep 17 00:00:00 2001
From: "lei.yang@windriver.com" <lei.yang@windriver.com>
Date: Tue, 17 Oct 2017 15:06:48 +0800
Subject: selftests: add missing test result status in memory-hotplug test

it only prints FAIL status when test fails, but doesn't print PASS
status when test pass,this patch is to add PASS status in the test log.

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/memory-hotplug/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 23db11c94b59..86636d207adf 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -4,10 +4,10 @@ all:
 include ../lib.mk
 
 TEST_PROGS := mem-on-off-test.sh
-override RUN_TESTS := ./mem-on-off-test.sh -r 2 || echo "selftests: memory-hotplug [FAIL]"
+override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
 override EMIT_TESTS := echo "$(RUN_TESTS)"
 
 run_full_test:
-	@/bin/bash ./mem-on-off-test.sh || echo "memory-hotplug selftests: [FAIL]"
+	@/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
 
 clean:
-- 
cgit v1.2.3


From af7dc093467a917278ec3b61aea46377b4372d8c Mon Sep 17 00:00:00 2001
From: Sumit Semwal <sumit.semwal@linaro.org>
Date: Mon, 23 Oct 2017 13:12:22 +0530
Subject: selftests: breakpoints: fix compile error on breakpoint_test_arm64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current mainline breakpoints test for arm64 fails to compile with

breakpoint_test_arm64.c: In function ‘set_watchpoint’:
breakpoint_test_arm64.c:97:28: error: storage size of ‘dreg_state’ isn’t known
  struct user_hwdebug_state dreg_state;

Adding a direct include for asm/ptrace.h helps it to build, and passes
the test on mainline on hikey.

Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/breakpoints/breakpoint_test_arm64.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
index 960d02100c26..2d95e5adde72 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
@@ -19,6 +19,7 @@
 
 #define _GNU_SOURCE
 
+#include <asm/ptrace.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <sys/ptrace.h>
-- 
cgit v1.2.3


From 8d17a6fe5d3cd635b48818b8da58a0e3ca4c2553 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Fri, 27 Oct 2017 15:10:30 +0900
Subject: selftests/ftrace: Do not use arch dependent do_IRQ as a target
 function

Instead using arch-dependent do_IRQ, use do_softirq as a
target function.

Applying do_IRQ to set_ftrace_filter always fail on arm/arm64 and any
other architectures which don't define do_IRQ. So, instead of using
that, use do_softirq which is defined in kernel/softirq.c.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index 5ad723724adb..c4f78ccaa908 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -33,7 +33,7 @@ do_reset
 
 FILTER=set_ftrace_filter
 FUNC1="schedule"
-FUNC2="do_IRQ"
+FUNC2="do_softirq"
 
 ALL_FUNCS="#### all functions enabled ####"
 
-- 
cgit v1.2.3


From 2650554da3f895a7bc276127dac4ec43b7b860c0 Mon Sep 17 00:00:00 2001
From: Greg Hackmann <ghackmann@google.com>
Date: Wed, 1 Nov 2017 14:34:26 -0700
Subject: selftests: vdso_test: support ARM64 targets

ARM64's vDSO exports its gettimeofday() implementation with a different
name (__kernel_gettimeofday) and version (LINUX_2.6.39) from other
architectures.  Add a corresponding special-case to vdso_test.

Signed-off-by: Greg Hackmann <ghackmann@google.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/vDSO/vdso_test.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vDSO/vdso_test.c b/tools/testing/selftests/vDSO/vdso_test.c
index 8daeb7d7032c..2df26bd0099c 100644
--- a/tools/testing/selftests/vDSO/vdso_test.c
+++ b/tools/testing/selftests/vDSO/vdso_test.c
@@ -19,6 +19,19 @@ extern void *vdso_sym(const char *version, const char *name);
 extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
 extern void vdso_init_from_auxv(void *auxv);
 
+/*
+ * ARM64's vDSO exports its gettimeofday() implementation with a different
+ * name and version from other architectures, so we need to handle it as
+ * a special case.
+ */
+#if defined(__aarch64__)
+const char *version = "LINUX_2.6.39";
+const char *name = "__kernel_gettimeofday";
+#else
+const char *version = "LINUX_2.6";
+const char *name = "__vdso_gettimeofday";
+#endif
+
 int main(int argc, char **argv)
 {
 	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
@@ -31,10 +44,10 @@ int main(int argc, char **argv)
 
 	/* Find gettimeofday. */
 	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
-	gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+	gtod_t gtod = (gtod_t)vdso_sym(version, name);
 
 	if (!gtod) {
-		printf("Could not find __vdso_gettimeofday\n");
+		printf("Could not find %s\n", name);
 		return 1;
 	}
 
@@ -45,7 +58,7 @@ int main(int argc, char **argv)
 		printf("The time is %lld.%06lld\n",
 		       (long long)tv.tv_sec, (long long)tv.tv_usec);
 	} else {
-		printf("__vdso_gettimeofday failed\n");
+		printf("%s failed\n", name);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 50656ac6acfbc42d30071983205e8f6b131429e5 Mon Sep 17 00:00:00 2001
From: "lei.yang@windriver.com" <lei.yang@windriver.com>
Date: Wed, 18 Oct 2017 10:10:23 +0800
Subject: selftests: remove obsolete kconfig fragment for cpu-hotplug

Kconfig CONFIG_CPU_NOTIFIER_ERROR_INJECT has been removed since kernel 4.10
check commit:
    commit 530e9b76ae8f863dfdef4a6ad0b38613d32e8c3f
    Author: Thomas Gleixner <tglx@linutronix.de>
    Date:   Wed Dec 21 20:19:53 2016 +0100

        cpu/hotplug: Remove obsolete cpu hotplug register/unregister
        functions

        hotcpu_notifier(), cpu_notifier(), __hotcpu_notifier(),
        __cpu_notifier(),
        register_hotcpu_notifier(), register_cpu_notifier(),
        __register_hotcpu_notifier(), __register_cpu_notifier(),
        unregister_hotcpu_notifier(), unregister_cpu_notifier(),
        __unregister_hotcpu_notifier(), __unregister_cpu_notifier()
     <snip>

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/cpu-hotplug/config | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/cpu-hotplug/config b/tools/testing/selftests/cpu-hotplug/config
index e6ab090cfbf3..d4aca2ad5069 100644
--- a/tools/testing/selftests/cpu-hotplug/config
+++ b/tools/testing/selftests/cpu-hotplug/config
@@ -1,2 +1 @@
 CONFIG_NOTIFIER_ERROR_INJECTION=y
-CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
-- 
cgit v1.2.3


From 47a18c42d99268a25689ecfac9e28c24af13d104 Mon Sep 17 00:00:00 2001
From: Pintu Agarwal <pintu.ping@gmail.com>
Date: Wed, 1 Nov 2017 13:00:39 -0400
Subject: android/ion: userspace test utility for ion buffer sharing

This is a test utility to verify ION buffer sharing in user space
between 2 independent processes.
It uses unix domain socket (with SCM_RIGHTS) as IPC to transfer an FD to
another process to share the same buffer.
This utility demonstrates how ION buffer sharing can be implemented between
two user space processes, using various heap types.

This utility is made to be run as part of kselftest framework in kernel.
The utility is verified on Ubuntu-32 bit system with Linux Kernel 4.14,
using ION system heap.

For more information about the utility please check the README file.

Signed-off-by: Pintu Agarwal <pintu.ping@gmail.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/Makefile                   |   3 +-
 tools/testing/selftests/android/Makefile           |  46 ++++
 tools/testing/selftests/android/ion/.gitignore     |   2 +
 tools/testing/selftests/android/ion/Makefile       |  16 ++
 tools/testing/selftests/android/ion/README         | 101 ++++++++
 tools/testing/selftests/android/ion/config         |   4 +
 tools/testing/selftests/android/ion/ion.h          | 143 ++++++++++++
 tools/testing/selftests/android/ion/ion_test.sh    |  55 +++++
 .../testing/selftests/android/ion/ionapp_export.c  | 135 +++++++++++
 .../testing/selftests/android/ion/ionapp_import.c  |  88 +++++++
 tools/testing/selftests/android/ion/ionutils.c     | 259 +++++++++++++++++++++
 tools/testing/selftests/android/ion/ionutils.h     |  55 +++++
 tools/testing/selftests/android/ion/ipcsocket.c    | 227 ++++++++++++++++++
 tools/testing/selftests/android/ion/ipcsocket.h    |  35 +++
 tools/testing/selftests/android/run.sh             |   3 +
 15 files changed, 1171 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/android/Makefile
 create mode 100644 tools/testing/selftests/android/ion/.gitignore
 create mode 100644 tools/testing/selftests/android/ion/Makefile
 create mode 100644 tools/testing/selftests/android/ion/README
 create mode 100644 tools/testing/selftests/android/ion/config
 create mode 100644 tools/testing/selftests/android/ion/ion.h
 create mode 100755 tools/testing/selftests/android/ion/ion_test.sh
 create mode 100644 tools/testing/selftests/android/ion/ionapp_export.c
 create mode 100644 tools/testing/selftests/android/ion/ionapp_import.c
 create mode 100644 tools/testing/selftests/android/ion/ionutils.c
 create mode 100644 tools/testing/selftests/android/ion/ionutils.h
 create mode 100644 tools/testing/selftests/android/ion/ipcsocket.c
 create mode 100644 tools/testing/selftests/android/ion/ipcsocket.h
 create mode 100755 tools/testing/selftests/android/run.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 3c9c0bbe7dbb..eaf599dc2137 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-TARGETS =  bpf
+TARGETS = android
+TARGETS += bpf
 TARGETS += breakpoints
 TARGETS += capabilities
 TARGETS += cpufreq
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
new file mode 100644
index 000000000000..1a7492268993
--- /dev/null
+++ b/tools/testing/selftests/android/Makefile
@@ -0,0 +1,46 @@
+SUBDIRS := ion
+
+TEST_PROGS := run.sh
+
+.PHONY: all clean
+
+include ../lib.mk
+
+all:
+	@for DIR in $(SUBDIRS); do		\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
+		mkdir $$BUILD_TARGET  -p;	\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+		#SUBDIR test prog name should be in the form: SUBDIR_test.sh
+		TEST=$$DIR"_test.sh"; \
+		if [ -e $$DIR/$$TEST ]; then
+			rsync -a $$DIR/$$TEST $$BUILD_TARGET/;
+		fi
+	done
+
+override define RUN_TESTS
+	@cd $(OUTPUT); ./run.sh
+endef
+
+override define INSTALL_RULE
+	mkdir -p $(INSTALL_PATH)
+	install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
+
+	@for SUBDIR in $(SUBDIRS); do \
+		BUILD_TARGET=$(OUTPUT)/$$SUBDIR;	\
+		mkdir $$BUILD_TARGET  -p;	\
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
+	done;
+endef
+
+override define EMIT_TESTS
+	echo "./run.sh"
+endef
+
+override define CLEAN
+	@for DIR in $(SUBDIRS); do		\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
+		mkdir $$BUILD_TARGET  -p;	\
+		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+	done
+endef
diff --git a/tools/testing/selftests/android/ion/.gitignore b/tools/testing/selftests/android/ion/.gitignore
new file mode 100644
index 000000000000..67e6f391b2a9
--- /dev/null
+++ b/tools/testing/selftests/android/ion/.gitignore
@@ -0,0 +1,2 @@
+ionapp_export
+ionapp_import
diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile
new file mode 100644
index 000000000000..96e0c448b39d
--- /dev/null
+++ b/tools/testing/selftests/android/ion/Makefile
@@ -0,0 +1,16 @@
+
+INCLUDEDIR := -I. -I../../../../../drivers/staging/android/uapi/
+CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
+
+TEST_GEN_FILES := ionapp_export ionapp_import
+
+all: $(TEST_GEN_FILES)
+
+$(TEST_GEN_FILES): ipcsocket.c ionutils.c
+
+TEST_PROGS := ion_test.sh
+
+include ../../lib.mk
+
+$(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
+$(OUTPUT)/ionapp_import: ionapp_import.c ipcsocket.c ionutils.c
diff --git a/tools/testing/selftests/android/ion/README b/tools/testing/selftests/android/ion/README
new file mode 100644
index 000000000000..21783e9c451e
--- /dev/null
+++ b/tools/testing/selftests/android/ion/README
@@ -0,0 +1,101 @@
+ION BUFFER SHARING UTILITY
+==========================
+File: ion_test.sh : Utility to test ION driver buffer sharing mechanism.
+Author: Pintu Kumar <pintu.ping@gmail.com>
+
+Introduction:
+-------------
+This is a test utility to verify ION buffer sharing in user space
+between 2 independent processes.
+It uses unix domain socket (with SCM_RIGHTS) as IPC to transfer an FD to
+another process to share the same buffer.
+This utility demonstrates how ION buffer sharing can be implemented between
+two user space processes, using various heap types.
+The following heap types are supported by ION driver.
+ION_HEAP_TYPE_SYSTEM (0)
+ION_HEAP_TYPE_SYSTEM_CONTIG (1)
+ION_HEAP_TYPE_CARVEOUT (2)
+ION_HEAP_TYPE_CHUNK (3)
+ION_HEAP_TYPE_DMA (4)
+
+By default only the SYSTEM and SYSTEM_CONTIG heaps are supported.
+Each heap is associated with the respective heap id.
+This utility is designed in the form of client/server program.
+The server part (ionapp_export) is the exporter of the buffer.
+It is responsible for creating an ION client, allocating the buffer based on
+the heap id, writing some data to this buffer and then exporting the FD
+(associated with this buffer) to another process using socket IPC.
+This FD is called as buffer FD (which is different than the ION client FD).
+
+The client part (ionapp_import) is the importer of the buffer.
+It retrives the FD from the socket data and installs into its address space.
+This new FD internally points to the same kernel buffer.
+So first it reads the data that is stored in this buffer and prints it.
+Then it writes the different size of data (it could be different data) to the
+same buffer.
+Finally the buffer FD must be closed by both the exporter and importer.
+Thus the same kernel buffer is shared among two user space processes using
+ION driver and only one time allocation.
+
+Prerequisite:
+-------------
+This utility works only if /dev/ion interface is present.
+The following configs needs to be enabled in kernel to include ion driver.
+CONFIG_ANDROID=y
+CONFIG_STAGING=y
+CONFIG_ION=y
+CONFIG_ION_SYSTEM_HEAP=y
+
+This utility requires to be run as root user.
+
+
+Compile and test:
+-----------------
+This utility is made to be run as part of kselftest framework in kernel.
+To compile and run using kselftest you can simply do the following from the
+kernel top directory.
+linux$ make TARGETS=android kselftest
+Or you can also use:
+linux$ make -C tools/testing/selftests TARGETS=android run_tests
+Using the selftest it can directly execute the ion_test.sh script to test the
+buffer sharing using ion system heap.
+Currently the heap size is hard coded as just 10 bytes inside this script.
+You need to be a root user to run under selftest.
+
+You can also compile and test manually using the following steps:
+ion$ make
+These will generate 2 executable: ionapp_export, ionapp_import
+Now you can run the export and import manually by specifying the heap type
+and the heap size.
+You can also directly execute the shell script to run the test automatically.
+Simply use the following command to run the test.
+ion$ sudo ./ion_test.sh
+
+Test Results:
+-------------
+The utility is verified on Ubuntu-32 bit system with Linux Kernel 4.14.
+Here is the snapshot of the test result using kselftest.
+
+linux# make TARGETS=android kselftest
+heap_type: 0, heap_size: 10
+--------------------------------------
+heap type: 0
+  heap id: 1
+heap name: ion_system_heap
+--------------------------------------
+Fill buffer content:
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
+Sharing fd: 6, Client fd: 5
+<ion_close_buffer_fd>: buffer release successfully....
+Received buffer fd: 4
+Read buffer content:
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0x0 0x0 0x0 0x0 0x0 0x0
+0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0
+Fill buffer content:
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
+0xfd 0xfd
+<ion_close_buffer_fd>: buffer release successfully....
+ion_test.sh: heap_type: 0 - [PASS]
+
+ion_test.sh: done
diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/ion/config
new file mode 100644
index 000000000000..19db6ca9aa2b
--- /dev/null
+++ b/tools/testing/selftests/android/ion/config
@@ -0,0 +1,4 @@
+CONFIG_ANDROID=y
+CONFIG_STAGING=y
+CONFIG_ION=y
+CONFIG_ION_SYSTEM_HEAP=y
diff --git a/tools/testing/selftests/android/ion/ion.h b/tools/testing/selftests/android/ion/ion.h
new file mode 100644
index 000000000000..f7021ac51335
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ion.h
@@ -0,0 +1,143 @@
+/*
+ * ion.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ */
+
+/* This file is copied from drivers/staging/android/uapi/ion.h
+ * This local copy is required for the selftest to pass, when build
+ * outside the kernel source tree.
+ * Please keep this file in sync with its original file until the
+ * ion driver is moved outside the staging tree.
+ */
+
+#ifndef _UAPI_LINUX_ION_H
+#define _UAPI_LINUX_ION_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * enum ion_heap_types - list of all possible types of heaps
+ * @ION_HEAP_TYPE_SYSTEM:	 memory allocated via vmalloc
+ * @ION_HEAP_TYPE_SYSTEM_CONTIG: memory allocated via kmalloc
+ * @ION_HEAP_TYPE_CARVEOUT:	 memory allocated from a prereserved
+ *				 carveout heap, allocations are physically
+ *				 contiguous
+ * @ION_HEAP_TYPE_DMA:		 memory allocated via DMA API
+ * @ION_NUM_HEAPS:		 helper for iterating over heaps, a bit mask
+ *				 is used to identify the heaps, so only 32
+ *				 total heap types are supported
+ */
+enum ion_heap_type {
+	ION_HEAP_TYPE_SYSTEM,
+	ION_HEAP_TYPE_SYSTEM_CONTIG,
+	ION_HEAP_TYPE_CARVEOUT,
+	ION_HEAP_TYPE_CHUNK,
+	ION_HEAP_TYPE_DMA,
+	ION_HEAP_TYPE_CUSTOM, /*
+			       * must be last so device specific heaps always
+			       * are at the end of this enum
+			       */
+};
+
+#define ION_NUM_HEAP_IDS		(sizeof(unsigned int) * 8)
+
+/**
+ * allocation flags - the lower 16 bits are used by core ion, the upper 16
+ * bits are reserved for use by the heaps themselves.
+ */
+
+/*
+ * mappings of this buffer should be cached, ion will do cache maintenance
+ * when the buffer is mapped for dma
+ */
+#define ION_FLAG_CACHED 1
+
+/**
+ * DOC: Ion Userspace API
+ *
+ * create a client by opening /dev/ion
+ * most operations handled via following ioctls
+ *
+ */
+
+/**
+ * struct ion_allocation_data - metadata passed from userspace for allocations
+ * @len:		size of the allocation
+ * @heap_id_mask:	mask of heap ids to allocate from
+ * @flags:		flags passed to heap
+ * @handle:		pointer that will be populated with a cookie to use to
+ *			refer to this allocation
+ *
+ * Provided by userspace as an argument to the ioctl
+ */
+struct ion_allocation_data {
+	__u64 len;
+	__u32 heap_id_mask;
+	__u32 flags;
+	__u32 fd;
+	__u32 unused;
+};
+
+#define MAX_HEAP_NAME			32
+
+/**
+ * struct ion_heap_data - data about a heap
+ * @name - first 32 characters of the heap name
+ * @type - heap type
+ * @heap_id - heap id for the heap
+ */
+struct ion_heap_data {
+	char name[MAX_HEAP_NAME];
+	__u32 type;
+	__u32 heap_id;
+	__u32 reserved0;
+	__u32 reserved1;
+	__u32 reserved2;
+};
+
+/**
+ * struct ion_heap_query - collection of data about all heaps
+ * @cnt - total number of heaps to be copied
+ * @heaps - buffer to copy heap data
+ */
+struct ion_heap_query {
+	__u32 cnt; /* Total number of heaps to be copied */
+	__u32 reserved0; /* align to 64bits */
+	__u64 heaps; /* buffer to be populated */
+	__u32 reserved1;
+	__u32 reserved2;
+};
+
+#define ION_IOC_MAGIC		'I'
+
+/**
+ * DOC: ION_IOC_ALLOC - allocate memory
+ *
+ * Takes an ion_allocation_data struct and returns it with the handle field
+ * populated with the opaque handle for the allocation.
+ */
+#define ION_IOC_ALLOC		_IOWR(ION_IOC_MAGIC, 0, \
+				      struct ion_allocation_data)
+
+/**
+ * DOC: ION_IOC_HEAP_QUERY - information about available heaps
+ *
+ * Takes an ion_heap_query structure and populates information about
+ * available Ion heaps.
+ */
+#define ION_IOC_HEAP_QUERY     _IOWR(ION_IOC_MAGIC, 8, \
+					struct ion_heap_query)
+
+#endif /* _UAPI_LINUX_ION_H */
diff --git a/tools/testing/selftests/android/ion/ion_test.sh b/tools/testing/selftests/android/ion/ion_test.sh
new file mode 100755
index 000000000000..a1aff506f5e6
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ion_test.sh
@@ -0,0 +1,55 @@
+#!/bin/bash
+
+heapsize=4096
+TCID="ion_test.sh"
+errcode=0
+
+run_test()
+{
+	heaptype=$1
+	./ionapp_export -i $heaptype -s $heapsize &
+	sleep 1
+	./ionapp_import
+	if [ $? -ne 0 ]; then
+		echo "$TCID: heap_type: $heaptype - [FAIL]"
+		errcode=1
+	else
+		echo "$TCID: heap_type: $heaptype - [PASS]"
+	fi
+	sleep 1
+	echo ""
+}
+
+check_root()
+{
+	uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo $TCID: must be run as root >&2
+		exit 0
+	fi
+}
+
+check_device()
+{
+	DEVICE=/dev/ion
+	if [ ! -e $DEVICE ]; then
+		echo $TCID: No $DEVICE device found >&2
+		echo $TCID: May be CONFIG_ION is not set >&2
+		exit 0
+	fi
+}
+
+main_function()
+{
+	check_device
+	check_root
+
+	# ION_SYSTEM_HEAP TEST
+	run_test 0
+	# ION_SYSTEM_CONTIG_HEAP TEST
+	run_test 1
+}
+
+main_function
+echo "$TCID: done"
+exit $errcode
diff --git a/tools/testing/selftests/android/ion/ionapp_export.c b/tools/testing/selftests/android/ion/ionapp_export.c
new file mode 100644
index 000000000000..a944e72621a9
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionapp_export.c
@@ -0,0 +1,135 @@
+/*
+ * ionapp_export.c
+ *
+ * It is a user space utility to create and export android
+ * ion memory buffer fd to another process using unix domain socket as IPC.
+ * This acts like a server for ionapp_import(client).
+ * So, this server has to be started first before the client.
+ *
+ * Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/time.h>
+#include "ionutils.h"
+#include "ipcsocket.h"
+
+
+void print_usage(int argc, char *argv[])
+{
+	printf("Usage: %s [-h <help>] [-i <heap id>] [-s <size in bytes>]\n",
+		argv[0]);
+}
+
+int main(int argc, char *argv[])
+{
+	int opt, ret, status, heapid;
+	int sockfd, client_fd, shared_fd;
+	unsigned char *map_buf;
+	unsigned long map_len, heap_type, heap_size, flags;
+	struct ion_buffer_info info;
+	struct socket_info skinfo;
+
+	if (argc < 2) {
+		print_usage(argc, argv);
+		return -1;
+	}
+
+	heap_size = 0;
+	flags = 0;
+
+	while ((opt = getopt(argc, argv, "hi:s:")) != -1) {
+		switch (opt) {
+		case 'h':
+			print_usage(argc, argv);
+			exit(0);
+			break;
+		case 'i':
+			heapid = atoi(optarg);
+			switch (heapid) {
+			case 0:
+				heap_type = ION_HEAP_TYPE_SYSTEM;
+				break;
+			case 1:
+				heap_type = ION_HEAP_TYPE_SYSTEM_CONTIG;
+				break;
+			default:
+				printf("ERROR: heap type not supported\n");
+				exit(1);
+			}
+			break;
+		case 's':
+			heap_size = atoi(optarg);
+			break;
+		default:
+			print_usage(argc, argv);
+			exit(1);
+			break;
+		}
+	}
+
+	if (heap_size <= 0) {
+		printf("heap_size cannot be 0\n");
+		print_usage(argc, argv);
+		exit(1);
+	}
+
+	printf("heap_type: %ld, heap_size: %ld\n", heap_type, heap_size);
+	info.heap_type = heap_type;
+	info.heap_size = heap_size;
+	info.flag_type = flags;
+
+	/* This is server: open the socket connection first */
+	/* Here; 1 indicates server or exporter */
+	status = opensocket(&sockfd, SOCKET_NAME, 1);
+	if (status < 0) {
+		fprintf(stderr, "<%s>: Failed opensocket.\n", __func__);
+		goto err_socket;
+	}
+	skinfo.sockfd = sockfd;
+
+	ret = ion_export_buffer_fd(&info);
+	if (ret < 0) {
+		fprintf(stderr, "FAILED: ion_get_buffer_fd\n");
+		goto err_export;
+	}
+	client_fd = info.ionfd;
+	shared_fd = info.buffd;
+	map_buf = info.buffer;
+	map_len = info.buflen;
+	write_buffer(map_buf, map_len);
+
+	/* share ion buf fd with other user process */
+	printf("Sharing fd: %d, Client fd: %d\n", shared_fd, client_fd);
+	skinfo.datafd = shared_fd;
+	skinfo.buflen = map_len;
+
+	ret = socket_send_fd(&skinfo);
+	if (ret < 0) {
+		fprintf(stderr, "FAILED: socket_send_fd\n");
+		goto err_send;
+	}
+
+err_send:
+err_export:
+	ion_close_buffer_fd(&info);
+
+err_socket:
+	closesocket(sockfd, SOCKET_NAME);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/android/ion/ionapp_import.c b/tools/testing/selftests/android/ion/ionapp_import.c
new file mode 100644
index 000000000000..ae2d704cfa46
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionapp_import.c
@@ -0,0 +1,88 @@
+/*
+ * ionapp_import.c
+ *
+ * It is a user space utility to receive android ion memory buffer fd
+ * over unix domain socket IPC that can be exported by ionapp_export.
+ * This acts like a client for ionapp_export.
+ *
+ * Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include "ionutils.h"
+#include "ipcsocket.h"
+
+
+int main(void)
+{
+	int ret, status;
+	int sockfd, shared_fd;
+	unsigned char *map_buf;
+	unsigned long map_len;
+	struct ion_buffer_info info;
+	struct socket_info skinfo;
+
+	/* This is the client part. Here 0 means client or importer */
+	status = opensocket(&sockfd, SOCKET_NAME, 0);
+	if (status < 0) {
+		fprintf(stderr, "No exporter exists...\n");
+		ret = status;
+		goto err_socket;
+	}
+
+	skinfo.sockfd = sockfd;
+
+	ret = socket_receive_fd(&skinfo);
+	if (ret < 0) {
+		fprintf(stderr, "Failed: socket_receive_fd\n");
+		goto err_recv;
+	}
+
+	shared_fd = skinfo.datafd;
+	printf("Received buffer fd: %d\n", shared_fd);
+	if (shared_fd <= 0) {
+		fprintf(stderr, "ERROR: improper buf fd\n");
+		ret = -1;
+		goto err_fd;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.buffd = shared_fd;
+	info.buflen = ION_BUFFER_LEN;
+
+	ret = ion_import_buffer_fd(&info);
+	if (ret < 0) {
+		fprintf(stderr, "Failed: ion_use_buffer_fd\n");
+		goto err_import;
+	}
+
+	map_buf = info.buffer;
+	map_len = info.buflen;
+	read_buffer(map_buf, map_len);
+
+	/* Write probably new data to the same buffer again */
+	map_len = ION_BUFFER_LEN;
+	write_buffer(map_buf, map_len);
+
+err_import:
+	ion_close_buffer_fd(&info);
+err_fd:
+err_recv:
+err_socket:
+	closesocket(sockfd, SOCKET_NAME);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/android/ion/ionutils.c b/tools/testing/selftests/android/ion/ionutils.c
new file mode 100644
index 000000000000..ce69c14f51fa
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionutils.c
@@ -0,0 +1,259 @@
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <errno.h>
+//#include <stdint.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include "ionutils.h"
+#include "ipcsocket.h"
+
+
+void write_buffer(void *buffer, unsigned long len)
+{
+	int i;
+	unsigned char *ptr = (unsigned char *)buffer;
+
+	if (!ptr) {
+		fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
+		return;
+	}
+
+	printf("Fill buffer content:\n");
+	memset(ptr, 0xfd, len);
+	for (i = 0; i < len; i++)
+		printf("0x%x ", ptr[i]);
+	printf("\n");
+}
+
+void read_buffer(void *buffer, unsigned long len)
+{
+	int i;
+	unsigned char *ptr = (unsigned char *)buffer;
+
+	if (!ptr) {
+		fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
+		return;
+	}
+
+	printf("Read buffer content:\n");
+	for (i = 0; i < len; i++)
+		printf("0x%x ", ptr[i]);
+	printf("\n");
+}
+
+int ion_export_buffer_fd(struct ion_buffer_info *ion_info)
+{
+	int i, ret, ionfd, buffer_fd;
+	unsigned int heap_id;
+	unsigned long maplen;
+	unsigned char *map_buffer;
+	struct ion_allocation_data alloc_data;
+	struct ion_heap_query query;
+	struct ion_heap_data heap_data[MAX_HEAP_COUNT];
+
+	if (!ion_info) {
+		fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
+		return -1;
+	}
+
+	/* Create an ION client */
+	ionfd = open(ION_DEVICE, O_RDWR);
+	if (ionfd < 0) {
+		fprintf(stderr, "<%s>: Failed to open ion client: %s\n",
+			__func__, strerror(errno));
+		return -1;
+	}
+
+	memset(&query, 0, sizeof(query));
+	query.cnt = MAX_HEAP_COUNT;
+	query.heaps = (unsigned long int)&heap_data[0];
+	/* Query ION heap_id_mask from ION heap */
+	ret = ioctl(ionfd, ION_IOC_HEAP_QUERY, &query);
+	if (ret < 0) {
+		fprintf(stderr, "<%s>: Failed: ION_IOC_HEAP_QUERY: %s\n",
+			__func__, strerror(errno));
+		goto err_query;
+	}
+
+	heap_id = MAX_HEAP_COUNT + 1;
+	for (i = 0; i < query.cnt; i++) {
+		if (heap_data[i].type == ion_info->heap_type) {
+			printf("--------------------------------------\n");
+			printf("heap type: %d\n", heap_data[i].type);
+			printf("  heap id: %d\n", heap_data[i].heap_id);
+			printf("heap name: %s\n", heap_data[i].name);
+			printf("--------------------------------------\n");
+			heap_id = heap_data[i].heap_id;
+			break;
+		}
+	}
+
+	if (heap_id > MAX_HEAP_COUNT) {
+		fprintf(stderr, "<%s>: ERROR: heap type does not exists\n",
+			__func__);
+		goto err_heap;
+	}
+
+	alloc_data.len = ion_info->heap_size;
+	alloc_data.heap_id_mask = 1 << heap_id;
+	alloc_data.flags = ion_info->flag_type;
+
+	/* Allocate memory for this ION client as per heap_type */
+	ret = ioctl(ionfd, ION_IOC_ALLOC, &alloc_data);
+	if (ret < 0) {
+		fprintf(stderr, "<%s>: Failed: ION_IOC_ALLOC: %s\n",
+			__func__, strerror(errno));
+		goto err_alloc;
+	}
+
+	/* This will return a valid buffer fd */
+	buffer_fd = alloc_data.fd;
+	maplen = alloc_data.len;
+
+	if (buffer_fd < 0 || maplen <= 0) {
+		fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
+			__func__, buffer_fd, maplen);
+		goto err_fd_data;
+	}
+
+	/* Create memory mapped buffer for the buffer fd */
+	map_buffer = (unsigned char *)mmap(NULL, maplen, PROT_READ|PROT_WRITE,
+			MAP_SHARED, buffer_fd, 0);
+	if (map_buffer == MAP_FAILED) {
+		fprintf(stderr, "<%s>: Failed: mmap: %s\n",
+			__func__, strerror(errno));
+		goto err_mmap;
+	}
+
+	ion_info->ionfd = ionfd;
+	ion_info->buffd = buffer_fd;
+	ion_info->buffer = map_buffer;
+	ion_info->buflen = maplen;
+
+	return 0;
+
+	munmap(map_buffer, maplen);
+
+err_fd_data:
+err_mmap:
+	/* in case of error: close the buffer fd */
+	if (buffer_fd)
+		close(buffer_fd);
+
+err_query:
+err_heap:
+err_alloc:
+	/* In case of error: close the ion client fd */
+	if (ionfd)
+		close(ionfd);
+
+	return -1;
+}
+
+int ion_import_buffer_fd(struct ion_buffer_info *ion_info)
+{
+	int buffd;
+	unsigned char *map_buf;
+	unsigned long map_len;
+
+	if (!ion_info) {
+		fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
+		return -1;
+	}
+
+	map_len = ion_info->buflen;
+	buffd = ion_info->buffd;
+
+	if (buffd < 0 || map_len <= 0) {
+		fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
+			__func__, buffd, map_len);
+		goto err_buffd;
+	}
+
+	map_buf = (unsigned char *)mmap(NULL, map_len, PROT_READ|PROT_WRITE,
+			MAP_SHARED, buffd, 0);
+	if (map_buf == MAP_FAILED) {
+		printf("<%s>: Failed - mmap: %s\n",
+			__func__, strerror(errno));
+		goto err_mmap;
+	}
+
+	ion_info->buffer = map_buf;
+	ion_info->buflen = map_len;
+
+	return 0;
+
+err_mmap:
+	if (buffd)
+		close(buffd);
+
+err_buffd:
+	return -1;
+}
+
+void ion_close_buffer_fd(struct ion_buffer_info *ion_info)
+{
+	if (ion_info) {
+		/* unmap the buffer properly in the end */
+		munmap(ion_info->buffer, ion_info->buflen);
+		/* close the buffer fd */
+		if (ion_info->buffd > 0)
+			close(ion_info->buffd);
+		/* Finally, close the client fd */
+		if (ion_info->ionfd > 0)
+			close(ion_info->ionfd);
+		printf("<%s>: buffer release successfully....\n", __func__);
+	}
+}
+
+int socket_send_fd(struct socket_info *info)
+{
+	int status;
+	int fd, sockfd;
+	struct socketdata skdata;
+
+	if (!info) {
+		fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
+		return -1;
+	}
+
+	sockfd = info->sockfd;
+	fd = info->datafd;
+	memset(&skdata, 0, sizeof(skdata));
+	skdata.data = fd;
+	skdata.len = sizeof(skdata.data);
+	status = sendtosocket(sockfd, &skdata);
+	if (status < 0) {
+		fprintf(stderr, "<%s>: Failed: sendtosocket\n", __func__);
+		return -1;
+	}
+
+	return 0;
+}
+
+int socket_receive_fd(struct socket_info *info)
+{
+	int status;
+	int fd, sockfd;
+	struct socketdata skdata;
+
+	if (!info) {
+		fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
+		return -1;
+	}
+
+	sockfd = info->sockfd;
+	memset(&skdata, 0, sizeof(skdata));
+	status = receivefromsocket(sockfd, &skdata);
+	if (status < 0) {
+		fprintf(stderr, "<%s>: Failed: receivefromsocket\n", __func__);
+		return -1;
+	}
+
+	fd = (int)skdata.data;
+	info->datafd = fd;
+
+	return status;
+}
diff --git a/tools/testing/selftests/android/ion/ionutils.h b/tools/testing/selftests/android/ion/ionutils.h
new file mode 100644
index 000000000000..9941eb858576
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionutils.h
@@ -0,0 +1,55 @@
+#ifndef __ION_UTILS_H
+#define __ION_UTILS_H
+
+#include "ion.h"
+
+#define SOCKET_NAME "ion_socket"
+#define ION_DEVICE "/dev/ion"
+
+#define ION_BUFFER_LEN	4096
+#define MAX_HEAP_COUNT	ION_HEAP_TYPE_CUSTOM
+
+struct socket_info {
+	int sockfd;
+	int datafd;
+	unsigned long buflen;
+};
+
+struct ion_buffer_info {
+	int ionfd;
+	int buffd;
+	unsigned int heap_type;
+	unsigned int flag_type;
+	unsigned long heap_size;
+	unsigned long buflen;
+	unsigned char *buffer;
+};
+
+
+/* This is used to fill the data into the mapped buffer */
+void write_buffer(void *buffer, unsigned long len);
+
+/* This is used to read the data from the exported buffer */
+void read_buffer(void *buffer, unsigned long len);
+
+/* This is used to create an ION buffer FD for the kernel buffer
+ * So you can export this same buffer to others in the form of FD
+ */
+int ion_export_buffer_fd(struct ion_buffer_info *ion_info);
+
+/* This is used to import or map an exported FD.
+ * So we point to same buffer without making a copy. Hence zero-copy.
+ */
+int ion_import_buffer_fd(struct ion_buffer_info *ion_info);
+
+/* This is used to close all references for the ION client */
+void ion_close_buffer_fd(struct ion_buffer_info *ion_info);
+
+/* This is used to send FD to another process using socket IPC */
+int socket_send_fd(struct socket_info *skinfo);
+
+/* This is used to receive FD from another process using socket IPC */
+int socket_receive_fd(struct socket_info *skinfo);
+
+
+#endif
diff --git a/tools/testing/selftests/android/ion/ipcsocket.c b/tools/testing/selftests/android/ion/ipcsocket.c
new file mode 100644
index 000000000000..7dc521002095
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ipcsocket.c
@@ -0,0 +1,227 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/un.h>
+#include <errno.h>
+
+#include "ipcsocket.h"
+
+
+int opensocket(int *sockfd, const char *name, int connecttype)
+{
+	int ret, temp = 1;
+
+	if (!name || strlen(name) > MAX_SOCK_NAME_LEN) {
+		fprintf(stderr, "<%s>: Invalid socket name.\n", __func__);
+		return -1;
+	}
+
+	ret = socket(PF_LOCAL, SOCK_STREAM, 0);
+	if (ret < 0) {
+		fprintf(stderr, "<%s>: Failed socket: <%s>\n",
+			__func__, strerror(errno));
+		return ret;
+	}
+
+	*sockfd = ret;
+	if (setsockopt(*sockfd, SOL_SOCKET, SO_REUSEADDR,
+		(char *)&temp, sizeof(int)) < 0) {
+		fprintf(stderr, "<%s>: Failed setsockopt: <%s>\n",
+		__func__, strerror(errno));
+		goto err;
+	}
+
+	sprintf(sock_name, "/tmp/%s", name);
+
+	if (connecttype == 1) {
+		/* This is for Server connection */
+		struct sockaddr_un skaddr;
+		int clientfd;
+		socklen_t sklen;
+
+		unlink(sock_name);
+		memset(&skaddr, 0, sizeof(skaddr));
+		skaddr.sun_family = AF_LOCAL;
+		strcpy(skaddr.sun_path, sock_name);
+
+		ret = bind(*sockfd, (struct sockaddr *)&skaddr,
+			SUN_LEN(&skaddr));
+		if (ret < 0) {
+			fprintf(stderr, "<%s>: Failed bind: <%s>\n",
+			__func__, strerror(errno));
+			goto err;
+		}
+
+		ret = listen(*sockfd, 5);
+		if (ret < 0) {
+			fprintf(stderr, "<%s>: Failed listen: <%s>\n",
+			__func__, strerror(errno));
+			goto err;
+		}
+
+		memset(&skaddr, 0, sizeof(skaddr));
+		sklen = sizeof(skaddr);
+
+		ret = accept(*sockfd, (struct sockaddr *)&skaddr,
+			(socklen_t *)&sklen);
+		if (ret < 0) {
+			fprintf(stderr, "<%s>: Failed accept: <%s>\n",
+			__func__, strerror(errno));
+			goto err;
+		}
+
+		clientfd = ret;
+		*sockfd = clientfd;
+	} else {
+		/* This is for client connection */
+		struct sockaddr_un skaddr;
+
+		memset(&skaddr, 0, sizeof(skaddr));
+		skaddr.sun_family = AF_LOCAL;
+		strcpy(skaddr.sun_path, sock_name);
+
+		ret = connect(*sockfd, (struct sockaddr *)&skaddr,
+			SUN_LEN(&skaddr));
+		if (ret < 0) {
+			fprintf(stderr, "<%s>: Failed connect: <%s>\n",
+			__func__, strerror(errno));
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	if (*sockfd)
+		close(*sockfd);
+
+	return ret;
+}
+
+int sendtosocket(int sockfd, struct socketdata *skdata)
+{
+	int ret, buffd;
+	unsigned int len;
+	char cmsg_b[CMSG_SPACE(sizeof(int))];
+	struct cmsghdr *cmsg;
+	struct msghdr msgh;
+	struct iovec iov;
+	struct timeval timeout;
+	fd_set selFDs;
+
+	if (!skdata) {
+		fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
+		return -1;
+	}
+
+	FD_ZERO(&selFDs);
+	FD_SET(0, &selFDs);
+	FD_SET(sockfd, &selFDs);
+	timeout.tv_sec = 20;
+	timeout.tv_usec = 0;
+
+	ret = select(sockfd+1, NULL, &selFDs, NULL, &timeout);
+	if (ret < 0) {
+		fprintf(stderr, "<%s>: Failed select: <%s>\n",
+		__func__, strerror(errno));
+		return -1;
+	}
+
+	if (FD_ISSET(sockfd, &selFDs)) {
+		buffd = skdata->data;
+		len = skdata->len;
+		memset(&msgh, 0, sizeof(msgh));
+		msgh.msg_control = &cmsg_b;
+		msgh.msg_controllen = CMSG_LEN(len);
+		iov.iov_base = "OK";
+		iov.iov_len = 2;
+		msgh.msg_iov = &iov;
+		msgh.msg_iovlen = 1;
+		cmsg = CMSG_FIRSTHDR(&msgh);
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_type = SCM_RIGHTS;
+		cmsg->cmsg_len = CMSG_LEN(len);
+		memcpy(CMSG_DATA(cmsg), &buffd, len);
+
+		ret = sendmsg(sockfd, &msgh, MSG_DONTWAIT);
+		if (ret < 0) {
+			fprintf(stderr, "<%s>: Failed sendmsg: <%s>\n",
+			__func__, strerror(errno));
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+int receivefromsocket(int sockfd, struct socketdata *skdata)
+{
+	int ret, buffd;
+	unsigned int len = 0;
+	char cmsg_b[CMSG_SPACE(sizeof(int))];
+	struct cmsghdr *cmsg;
+	struct msghdr msgh;
+	struct iovec iov;
+	fd_set recvFDs;
+	char data[32];
+
+	if (!skdata) {
+		fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
+		return -1;
+	}
+
+	FD_ZERO(&recvFDs);
+	FD_SET(0, &recvFDs);
+	FD_SET(sockfd, &recvFDs);
+
+	ret = select(sockfd+1, &recvFDs, NULL, NULL, NULL);
+	if (ret < 0) {
+		fprintf(stderr, "<%s>: Failed select: <%s>\n",
+		__func__, strerror(errno));
+		return -1;
+	}
+
+	if (FD_ISSET(sockfd, &recvFDs)) {
+		len = sizeof(buffd);
+		memset(&msgh, 0, sizeof(msgh));
+		msgh.msg_control = &cmsg_b;
+		msgh.msg_controllen = CMSG_LEN(len);
+		iov.iov_base = data;
+		iov.iov_len = sizeof(data)-1;
+		msgh.msg_iov = &iov;
+		msgh.msg_iovlen = 1;
+		cmsg = CMSG_FIRSTHDR(&msgh);
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_type = SCM_RIGHTS;
+		cmsg->cmsg_len = CMSG_LEN(len);
+
+		ret = recvmsg(sockfd, &msgh, MSG_DONTWAIT);
+		if (ret < 0) {
+			fprintf(stderr, "<%s>: Failed recvmsg: <%s>\n",
+			__func__, strerror(errno));
+			return -1;
+		}
+
+		memcpy(&buffd, CMSG_DATA(cmsg), len);
+		skdata->data = buffd;
+		skdata->len = len;
+	}
+	return 0;
+}
+
+int closesocket(int sockfd, char *name)
+{
+	char sockname[MAX_SOCK_NAME_LEN];
+
+	if (sockfd)
+		close(sockfd);
+	sprintf(sockname, "/tmp/%s", name);
+	unlink(sockname);
+	shutdown(sockfd, 2);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/android/ion/ipcsocket.h b/tools/testing/selftests/android/ion/ipcsocket.h
new file mode 100644
index 000000000000..b3e84498a8a1
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ipcsocket.h
@@ -0,0 +1,35 @@
+
+#ifndef _IPCSOCKET_H
+#define _IPCSOCKET_H
+
+
+#define MAX_SOCK_NAME_LEN	64
+
+char sock_name[MAX_SOCK_NAME_LEN];
+
+/* This structure is responsible for holding the IPC data
+ * data: hold the buffer fd
+ * len: just the length of 32-bit integer fd
+ */
+struct socketdata {
+	int data;
+	unsigned int len;
+};
+
+/* This API is used to open the IPC socket connection
+ * name: implies a unique socket name in the system
+ * connecttype: implies server(0) or client(1)
+ */
+int opensocket(int *sockfd, const char *name, int connecttype);
+
+/* This is the API to send socket data over IPC socket */
+int sendtosocket(int sockfd, struct socketdata *data);
+
+/* This is the API to receive socket data over IPC socket */
+int receivefromsocket(int sockfd, struct socketdata *data);
+
+/* This is the API to close the socket connection */
+int closesocket(int sockfd, char *name);
+
+
+#endif
diff --git a/tools/testing/selftests/android/run.sh b/tools/testing/selftests/android/run.sh
new file mode 100755
index 000000000000..dd8edf291454
--- /dev/null
+++ b/tools/testing/selftests/android/run.sh
@@ -0,0 +1,3 @@
+#!/bin/sh
+
+(cd ion; ./ion_test.sh)
-- 
cgit v1.2.3


From f737b8f4d3c4b0e088492ee8b5134f5fe9f43b87 Mon Sep 17 00:00:00 2001
From: Lei Yang <Lei.Yang@windriver.com>
Date: Sat, 21 Oct 2017 18:17:50 +0800
Subject: selftests: ftrace: add more config fragments

We need to enable more configs to make test more
without this patch,we got lots of "UNSUPPORTED"

before the patch:
http://pastebin.ubuntu.com/25784377/
after the patch:
http://pastebin.ubuntu.com/25784387/

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/ftrace/config | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index 8a1c9f949fe0..b01924c71c09 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -1,2 +1,6 @@
 CONFIG_KPROBES=y
 CONFIG_FTRACE=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_TRACER_SNAPSHOT=y
+CONFIG_STACK_TRACER=y
+CONFIG_HIST_TRIGGERS=y
-- 
cgit v1.2.3


From 42534b1f58e04a5a6d245d4a8d25f7eb5fd79c7a Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 4 Nov 2017 04:38:41 +0900
Subject: selftests/ftrace: Introduce exit_pass and exit_fail

As same as other results, introduce exit_pass and exit_fail
functions so that we can easily understand what will happen.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/ftrace/ftracetest                          | 7 +++++++
 tools/testing/selftests/ftrace/test.d/00basic/basic4.tc            | 2 +-
 tools/testing/selftests/ftrace/test.d/event/event-enable.tc        | 2 +-
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc           | 2 +-
 tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc    | 2 +-
 tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc     | 2 +-
 .../testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc  | 2 +-
 tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc      | 2 +-
 tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc    | 2 +-
 .../testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc  | 5 ++---
 tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc      | 2 +-
 .../testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc | 2 +-
 .../selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc     | 2 +-
 tools/testing/selftests/ftrace/test.d/instances/instance-event.tc  | 2 +-
 tools/testing/selftests/ftrace/test.d/instances/instance.tc        | 2 +-
 tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc         | 2 +-
 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc        | 2 +-
 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc   | 2 +-
 tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc     | 2 +-
 tools/testing/selftests/ftrace/test.d/template                     | 1 +
 .../testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc  | 2 +-
 tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc    | 2 +-
 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc  | 2 +-
 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc      | 2 +-
 tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc | 2 +-
 tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc  | 2 +-
 .../testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc  | 2 +-
 .../testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc  | 2 +-
 28 files changed, 35 insertions(+), 28 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index abc706cf7702..f9a9d424c980 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -222,7 +222,14 @@ SIG_RESULT=
 SIG_BASE=36	# Use realtime signals
 SIG_PID=$$
 
+exit_pass () {
+  exit 0
+}
+
 SIG_FAIL=$((SIG_BASE + FAIL))
+exit_fail () {
+  exit 1
+}
 trap 'SIG_RESULT=$FAIL' $SIG_FAIL
 
 SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED))
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
index aa51f6c17359..0696098d6408 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
@@ -2,4 +2,4 @@
 # description: Basic event tracing check
 test -f available_events -a -f set_event -a -d events
 # check scheduler events are available
-grep -q sched available_events && exit 0 || exit $FAIL
+grep -q sched available_events && exit_pass || exit_fail
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
index 6ff851a75884..9daf034186f5 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -11,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index cc14feec6e1f..132478b305c2 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -13,7 +13,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index 85094904aa79..6a37a8642ee6 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -11,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
index cc1cf4d30ef5..4e9b6e2c0219 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -10,7 +10,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
index 45df747887e0..1aec99d108eb 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -28,7 +28,7 @@ do_reset() {
 fail() { # msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 disable_tracing
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
index 0387e22e7577..9f8d27ca39cf 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -18,7 +18,7 @@ do_reset() {
 fail() { # msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 disable_tracing
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 78524fcc25ae..524ce24b3c22 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -51,7 +51,7 @@ do_reset() {
 fail() { # msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
index 9d4afcca1e36..6fed4cf2db81 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
@@ -27,7 +27,7 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 SLEEP_TIME=".1"
@@ -48,8 +48,7 @@ test_event_enabled() {
 
     e=`cat $EVENT_ENABLE`
     if [ "$e" != $val ]; then
-	echo "Expected $val but found $e"
-	exit 1
+	fail "Expected $val but found $e"
     fi
 }
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
index fe0dc5a7ea26..b2d5a8febfe8 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -32,7 +32,7 @@ fail() { # mesg
     reset_tracer
     echo > set_ftrace_filter
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 echo "Testing function tracer with profiler:"
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index c4f78ccaa908..0f3f92622e33 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -26,7 +26,7 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 do_reset
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
index cdc92a371cd7..f6d9ac73268a 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
@@ -27,7 +27,7 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 SLEEP_TIME=".1"
diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
index d7f48b55df51..4fa0f79144f4 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
@@ -11,7 +11,7 @@ fail() { # mesg
     rmdir foo 2>/dev/null
     echo $1
     set -e
-    exit $FAIL
+    exit_fail
 }
 
 cd instances
diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
index ddda62203366..b84651283bf3 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
@@ -11,7 +11,7 @@ fail() { # mesg
     rmdir x y z 2>/dev/null
     echo $1
     set -e
-    exit $FAIL
+    exit_fail
 }
 
 cd instances
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index 0e6f415c6152..bbc443a9190c 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -9,7 +9,7 @@ echo > kprobe_events
 echo p:myevent _do_fork > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
-echo > kprobe_events && exit 1 # this must fail
+echo > kprobe_events && exit_fail # this must fail
 echo 0 > events/kprobes/myevent/enable
 echo > kprobe_events # this must succeed
 clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index 679bbd23bcc3..8b43c6804fc3 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -14,5 +14,5 @@ echo 1 > events/kprobes/testprobe/enable
 echo 0 > events/kprobes/testprobe/enable
 echo "-:testprobe" >> kprobe_events
 clear_trace
-test -d events/kprobes/testprobe && exit 1 || exit 0
+test -d events/kprobes/testprobe && exit_fail || exit_pass
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 17d33ba192f6..2a1755bfc290 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -35,4 +35,4 @@ check_types $ARGS
 
 echo "-:testprobe" >> kprobe_events
 clear_trace
-test -d events/kprobes/testprobe && exit 1 || exit 0
+test -d events/kprobes/testprobe && exit_fail || exit_pass
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index f1825bdbe3f3..321954683aaa 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -14,4 +14,4 @@ echo 1 > events/kprobes/testprobe2/enable
 echo 0 > events/kprobes/testprobe2/enable
 echo '-:testprobe2' >> kprobe_events
 clear_trace
-test -d events/kprobes/testprobe2 && exit 1 || exit 0
+test -d events/kprobes/testprobe2 && exit_fail || exit_pass
diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template
index 5448f7abad5f..5c39ceb18a0d 100644
--- a/tools/testing/selftests/ftrace/test.d/template
+++ b/tools/testing/selftests/ftrace/test.d/template
@@ -4,6 +4,7 @@
 # Note that all tests are run with "errexit" option.
 
 exit 0 # Return 0 if the test is passed, otherwise return !0
+# Or you can call exit_pass for passed test, and exit_fail for failed test.
 # If the test could not run because of lack of feature, call exit_unsupported
 # If the test returned unclear results, call exit_unresolved
 # If the test is a dummy, or a placeholder, call exit_untested
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
index 839ac4320b24..28cc355a3a7b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
@@ -12,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
index 66873c4b12c9..a48e23eb8a8b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
@@ -12,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index 4237b32769f1..8da80efc44d8 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -12,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
index d24e2b8bd863..449fe9ff91a2 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -12,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index 4c0774fff378..c5ef8b9d02b3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -12,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
index 3fc6321e081f..ed38f0050d77 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
@@ -11,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
index 3652824f81ed..3121d795a868 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
@@ -11,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
index 6d9051cdf408..c59d9eb546da 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
@@ -11,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
-- 
cgit v1.2.3


From 7d33d2b5b8581ed9f7b2ad93156cde223df718dc Mon Sep 17 00:00:00 2001
From: Lei Yang <Lei.Yang@windriver.com>
Date: Sun, 5 Nov 2017 18:56:40 +0800
Subject: selftests: memfd_test.c: fix compilation warning.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace '%d' by '%zu' to fix the following compilation warning.

memfd_test.c:517:3: warning: format ‘%d’ expects argument of
type ‘int’,but argument 2 has type ‘size_t’ [-Wformat=]
   printf("malloc(%d) failed: %m\n", mfd_def_size * 8);
   ^
memfd_test.c: In function ‘mfd_fail_grow_write’:
memfd_test.c:537:3: warning: format ‘%d’ expects argument
of type ‘int’,but argument 2 has type ‘size_t’ [-Wformat=]
   printf("malloc(%d) failed: %m\n", mfd_def_size * 8);

Signed-off-by: Lei Yang <Lei.Yang@windriver.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/memfd/memfd_test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 845e5f67b6f0..132a54f74e88 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -515,7 +515,7 @@ static void mfd_assert_grow_write(int fd)
 
 	buf = malloc(mfd_def_size * 8);
 	if (!buf) {
-		printf("malloc(%d) failed: %m\n", mfd_def_size * 8);
+		printf("malloc(%zu) failed: %m\n", mfd_def_size * 8);
 		abort();
 	}
 
@@ -535,7 +535,7 @@ static void mfd_fail_grow_write(int fd)
 
 	buf = malloc(mfd_def_size * 8);
 	if (!buf) {
-		printf("malloc(%d) failed: %m\n", mfd_def_size * 8);
+		printf("malloc(%zu) failed: %m\n", mfd_def_size * 8);
 		abort();
 	}
 
-- 
cgit v1.2.3


From 157339a14ac41c710333b2abc18f5a6f52204625 Mon Sep 17 00:00:00 2001
From: Amit Pundir <amit.pundir@linaro.org>
Date: Thu, 9 Nov 2017 01:10:34 +0530
Subject: selftests: firmware: skip unsupported async loading tests

Ignore async firmware loading tests on older kernel releases,
which do not support this feature.

Fixes: 1b1fe542b6f0:
       ("selftests: firmware: add empty string and async tests")
Reviewed-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Luis R. Rodriguez <mcgrof@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/firmware/fw_filesystem.sh | 34 ++++++++++++++---------
 1 file changed, 21 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 62f2d6f54929..b1f20fef36c7 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -70,9 +70,13 @@ if printf '\000' >"$DIR"/trigger_request 2> /dev/null; then
 	exit 1
 fi
 
-if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
-	echo "$0: empty filename should not succeed (async)" >&2
-	exit 1
+if [ ! -e "$DIR"/trigger_async_request ]; then
+	echo "$0: empty filename: async trigger not present, ignoring test" >&2
+else
+	if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
+		echo "$0: empty filename should not succeed (async)" >&2
+		exit 1
+	fi
 fi
 
 # Request a firmware that doesn't exist, it should fail.
@@ -105,17 +109,21 @@ else
 fi
 
 # Try the asynchronous version too
-if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
-	echo "$0: could not trigger async request" >&2
-	exit 1
-fi
-
-# Verify the contents are what we expect.
-if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
-	echo "$0: firmware was not loaded (async)" >&2
-	exit 1
+if [ ! -e "$DIR"/trigger_async_request ]; then
+	echo "$0: firmware loading: async trigger not present, ignoring test" >&2
 else
-	echo "$0: async filesystem loading works"
+	if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
+		echo "$0: could not trigger async request" >&2
+		exit 1
+	fi
+
+	# Verify the contents are what we expect.
+	if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+		echo "$0: firmware was not loaded (async)" >&2
+		exit 1
+	else
+		echo "$0: async filesystem loading works"
+	fi
 fi
 
 ### Batched requests tests
-- 
cgit v1.2.3


From c3e0d179bff503cd56758579a2c33216b40b9b7b Mon Sep 17 00:00:00 2001
From: Amit Pundir <amit.pundir@linaro.org>
Date: Thu, 9 Nov 2017 01:10:35 +0530
Subject: selftests: firmware: skip unsupported custom firmware fallback tests

Ignore custom firmware loading and cancellation tests on older
kernel releases, which do not support this feature.

Fixes: 061132d2b9c9 ("test_firmware: add test custom fallback trigger")
Reviewed-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Luis R. Rodriguez <mcgrof@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/firmware/fw_fallback.sh | 38 +++++++++++++++++--------
 1 file changed, 26 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh
index a52a3bab532b..34a42c68ebfb 100755
--- a/tools/testing/selftests/firmware/fw_fallback.sh
+++ b/tools/testing/selftests/firmware/fw_fallback.sh
@@ -86,6 +86,11 @@ load_fw_cancel()
 
 load_fw_custom()
 {
+	if [ ! -e "$DIR"/trigger_custom_fallback ]; then
+		echo "$0: custom fallback trigger not present, ignoring test" >&2
+		return 1
+	fi
+
 	local name="$1"
 	local file="$2"
 
@@ -108,11 +113,17 @@ load_fw_custom()
 
 	# Wait for request to finish.
 	wait
+	return 0
 }
 
 
 load_fw_custom_cancel()
 {
+	if [ ! -e "$DIR"/trigger_custom_fallback ]; then
+		echo "$0: canceling custom fallback trigger not present, ignoring test" >&2
+		return 1
+	fi
+
 	local name="$1"
 	local file="$2"
 
@@ -133,6 +144,7 @@ load_fw_custom_cancel()
 
 	# Wait for request to finish.
 	wait
+	return 0
 }
 
 load_fw_fallback_with_child()
@@ -227,20 +239,22 @@ else
 	echo "$0: cancelling fallback mechanism works"
 fi
 
-load_fw_custom "$NAME" "$FW"
-if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
-	echo "$0: firmware was not loaded" >&2
-	exit 1
-else
-	echo "$0: custom fallback loading mechanism works"
+if load_fw_custom "$NAME" "$FW" ; then
+	if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+		echo "$0: firmware was not loaded" >&2
+		exit 1
+	else
+		echo "$0: custom fallback loading mechanism works"
+	fi
 fi
 
-load_fw_custom_cancel "nope-$NAME" "$FW"
-if diff -q "$FW" /dev/test_firmware >/dev/null ; then
-	echo "$0: firmware was expected to be cancelled" >&2
-	exit 1
-else
-	echo "$0: cancelling custom fallback mechanism works"
+if load_fw_custom_cancel "nope-$NAME" "$FW" ; then
+	if diff -q "$FW" /dev/test_firmware >/dev/null ; then
+		echo "$0: firmware was expected to be cancelled" >&2
+		exit 1
+	else
+		echo "$0: cancelling custom fallback mechanism works"
+	fi
 fi
 
 set +e
-- 
cgit v1.2.3


From 53d1cd6b125fb9d69303516a1179ebc3b72f797a Mon Sep 17 00:00:00 2001
From: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Date: Tue, 7 Nov 2017 15:17:55 +0530
Subject: cpupowerutils: bench - Fix cpu online check

cpupower_is_cpu_online was incorrectly checking for 0. This patch fixes
this by checking for 1 when the cpu is online.

Signed-off-by: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/power/cpupower/bench/system.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/bench/system.c b/tools/power/cpupower/bench/system.c
index c25a74ae51ba..2bb3eef7d5c1 100644
--- a/tools/power/cpupower/bench/system.c
+++ b/tools/power/cpupower/bench/system.c
@@ -61,7 +61,7 @@ int set_cpufreq_governor(char *governor, unsigned int cpu)
 
 	dprintf("set %s as cpufreq governor\n", governor);
 
-	if (cpupower_is_cpu_online(cpu) != 0) {
+	if (cpupower_is_cpu_online(cpu) != 1) {
 		perror("cpufreq_cpu_exists");
 		fprintf(stderr, "error: cpu %u does not exist\n", cpu);
 		return -1;
-- 
cgit v1.2.3


From dbdc468f35ee827cab2753caa1c660bdb832243a Mon Sep 17 00:00:00 2001
From: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Date: Wed, 15 Nov 2017 14:10:02 +0530
Subject: cpupower : Fix cpupower working when cpu0 is offline

cpuidle_monitor used to assume that cpu0 is always online which is not
a valid assumption on POWER machines. This patch fixes this by getting
the cpu on which the current thread is running, instead of always using
cpu0 for monitoring which may not be online.

Signed-off-by: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
index 1b5da0066ebf..5b3205f16217 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
@@ -130,15 +130,18 @@ static struct cpuidle_monitor *cpuidle_register(void)
 {
 	int num;
 	char *tmp;
+	int this_cpu;
+
+	this_cpu = sched_getcpu();
 
 	/* Assume idle state count is the same for all CPUs */
-	cpuidle_sysfs_monitor.hw_states_num = cpuidle_state_count(0);
+	cpuidle_sysfs_monitor.hw_states_num = cpuidle_state_count(this_cpu);
 
 	if (cpuidle_sysfs_monitor.hw_states_num <= 0)
 		return NULL;
 
 	for (num = 0; num < cpuidle_sysfs_monitor.hw_states_num; num++) {
-		tmp = cpuidle_state_name(0, num);
+		tmp = cpuidle_state_name(this_cpu, num);
 		if (tmp == NULL)
 			continue;
 
@@ -146,7 +149,7 @@ static struct cpuidle_monitor *cpuidle_register(void)
 		strncpy(cpuidle_cstates[num].name, tmp, CSTATE_NAME_LEN - 1);
 		free(tmp);
 
-		tmp = cpuidle_state_desc(0, num);
+		tmp = cpuidle_state_desc(this_cpu, num);
 		if (tmp == NULL)
 			continue;
 		strncpy(cpuidle_cstates[num].desc, tmp,	CSTATE_DESC_LEN - 1);
-- 
cgit v1.2.3


From 7ad3f188aac15772c97523dc4ca3e8e5b6294b9c Mon Sep 17 00:00:00 2001
From: Yang Shi <yang.s@alibaba-inc.com>
Date: Wed, 15 Nov 2017 17:31:59 -0800
Subject: tools: slabinfo: add "-U" option to show unreclaimable slabs only

Patch series "oom: capture unreclaimable slab info in oom message", v10.

Recently we ran into a oom issue, kernel panic due to no killable
process.  The dmesg shows huge unreclaimable slabs used almost 100%
memory, but kdump doesn't capture vmcore due to some reason.

So, it may sound better to capture unreclaimable slab info in oom
message when kernel panic to aid trouble shooting and cover the corner
case.  Since kernel already panic, so capturing more information sounds
worthy and doesn't bother normal oom killer.

With the patchset, tools/vm/slabinfo has a new option, "-U", to show
unreclaimable slab only.

And, oom will print all non zero (num_objs * size != 0) unreclaimable
slabs in oom killer message.

This patch (of 3):

Add "-U" option to show unreclaimable slabs only.

"-U" and "-S" together can tell us what unreclaimable slabs use the most
memory to help debug huge unreclaimable slabs issue.

Link: http://lkml.kernel.org/r/1507152550-46205-2-git-send-email-yang.s@alibaba-inc.com
Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/vm/slabinfo.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index b0b7ef6d0de1..f82c2eaa859d 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -84,6 +84,7 @@ int output_lines = -1;
 int sort_loss;
 int extended_totals;
 int show_bytes;
+int unreclaim_only;
 
 /* Debug options */
 int sanity;
@@ -133,6 +134,7 @@ static void usage(void)
 		"-L|--Loss              Sort by loss\n"
 		"-X|--Xtotals           Show extended summary information\n"
 		"-B|--Bytes             Show size in bytes\n"
+		"-U|--Unreclaim		Show unreclaimable slabs only\n"
 		"\nValid debug options (FZPUT may be combined)\n"
 		"a / A          Switch on all debug options (=FZUP)\n"
 		"-              Switch off all debug options\n"
@@ -569,6 +571,9 @@ static void slabcache(struct slabinfo *s)
 	if (strcmp(s->name, "*") == 0)
 		return;
 
+	if (unreclaim_only && s->reclaim_account)
+		return;
+
 	if (actual_slabs == 1) {
 		report(s);
 		return;
@@ -1347,6 +1352,7 @@ struct option opts[] = {
 	{ "Loss", no_argument, NULL, 'L'},
 	{ "Xtotals", no_argument, NULL, 'X'},
 	{ "Bytes", no_argument, NULL, 'B'},
+	{ "Unreclaim", no_argument, NULL, 'U'},
 	{ NULL, 0, NULL, 0 }
 };
 
@@ -1358,7 +1364,7 @@ int main(int argc, char *argv[])
 
 	page_size = getpagesize();
 
-	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXB",
+	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXBU",
 						opts, NULL)) != -1)
 		switch (c) {
 		case '1':
@@ -1439,6 +1445,9 @@ int main(int argc, char *argv[])
 		case 'B':
 			show_bytes = 1;
 			break;
+		case 'U':
+			unreclaim_only = 1;
+			break;
 		default:
 			fatal("%s: Invalid option '%c'\n", argv[0], optopt);
 
-- 
cgit v1.2.3


From d8be75663cec0069b85f80191abd2682ce4a512f Mon Sep 17 00:00:00 2001
From: "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com>
Date: Wed, 15 Nov 2017 17:35:58 -0800
Subject: kmemcheck: remove whats left of NOTRACK flags

Now that kmemcheck is gone, we don't need the NOTRACK flags.

Link: http://lkml.kernel.org/r/20171007030159.22241-5-alexander.levin@verizon.com
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tim Hansen <devtimhansen@gmail.com>
Cc: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/pgtable.h       |  5 -----
 arch/x86/include/asm/pgtable_types.h | 13 -------------
 include/linux/gfp.h                  |  9 ---------
 include/linux/slab.h                 |  6 ------
 include/trace/events/mmflags.h       |  1 -
 mm/slub.c                            |  2 --
 tools/perf/builtin-kmem.c            |  1 -
 7 files changed, 37 deletions(-)

(limited to 'tools')

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f735c3016325..09f9e1e00e3b 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -667,11 +667,6 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 	return false;
 }
 
-static inline int pte_hidden(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_HIDDEN;
-}
-
 static inline int pmd_present(pmd_t pmd)
 {
 	/*
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9e9b05fc4860..3696398a9475 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -32,7 +32,6 @@
 
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
-#define _PAGE_BIT_HIDDEN	_PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
@@ -79,18 +78,6 @@
 #define _PAGE_KNL_ERRATUM_MASK 0
 #endif
 
-#ifdef CONFIG_KMEMCHECK
-#define _PAGE_HIDDEN	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
-#else
-#define _PAGE_HIDDEN	(_AT(pteval_t, 0))
-#endif
-
-/*
- * The same hidden bit is used by kmemcheck, but since kmemcheck
- * works on kernel pages while soft-dirty engine on user space,
- * they do not conflict with each other.
- */
-
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 710143741eb5..b041f94678de 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -37,7 +37,6 @@ struct vm_area_struct;
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_ATOMIC		0x80000u
 #define ___GFP_ACCOUNT		0x100000u
-#define ___GFP_NOTRACK		0x200000u
 #define ___GFP_DIRECT_RECLAIM	0x400000u
 #define ___GFP_WRITE		0x800000u
 #define ___GFP_KSWAPD_RECLAIM	0x1000000u
@@ -201,19 +200,11 @@ struct vm_area_struct;
  * __GFP_COMP address compound page metadata.
  *
  * __GFP_ZERO returns a zeroed page on success.
- *
- * __GFP_NOTRACK avoids tracking with kmemcheck.
- *
- * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of
- *   distinguishing in the source between false positives and allocations that
- *   cannot be supported (e.g. page tables).
  */
 #define __GFP_COLD	((__force gfp_t)___GFP_COLD)
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
-#define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)
-#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
diff --git a/include/linux/slab.h b/include/linux/slab.h
index ebddfca9e24b..79f6532f8a0b 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -89,12 +89,6 @@
 /* Avoid kmemleak tracing */
 #define SLAB_NOLEAKTRACE	((slab_flags_t __force)0x00800000U)
 
-/* Don't track use of uninitialized memory */
-#ifdef CONFIG_KMEMCHECK
-# define SLAB_NOTRACK		((slab_flags_t __force)0x01000000U)
-#else
-# define SLAB_NOTRACK		0
-#endif
 /* Fault injection mark */
 #ifdef CONFIG_FAILSLAB
 # define SLAB_FAILSLAB		((slab_flags_t __force)0x02000000U)
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 648cbf603736..72162f3a03fa 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -46,7 +46,6 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"__GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"__GFP_MOVABLE"},	\
 	{(unsigned long)__GFP_ACCOUNT,		"__GFP_ACCOUNT"},	\
-	{(unsigned long)__GFP_NOTRACK,		"__GFP_NOTRACK"},	\
 	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
 	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
 	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
diff --git a/mm/slub.c b/mm/slub.c
index 91aa99b4b836..c2c41e178acf 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5635,8 +5635,6 @@ static char *create_unique_id(struct kmem_cache *s)
 		*p++ = 'a';
 	if (s->flags & SLAB_CONSISTENCY_CHECKS)
 		*p++ = 'F';
-	if (!(s->flags & SLAB_NOTRACK))
-		*p++ = 't';
 	if (s->flags & SLAB_ACCOUNT)
 		*p++ = 'A';
 	if (p != name + 1)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 557d391f564a..cbf70738ef5f 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -655,7 +655,6 @@ static const struct {
 	{ "__GFP_RECLAIMABLE",		"RC" },
 	{ "__GFP_MOVABLE",		"M" },
 	{ "__GFP_ACCOUNT",		"AC" },
-	{ "__GFP_NOTRACK",		"NT" },
 	{ "__GFP_WRITE",		"WR" },
 	{ "__GFP_RECLAIM",		"R" },
 	{ "__GFP_DIRECT_RECLAIM",	"DR" },
-- 
cgit v1.2.3


From 4675ff05de2d76d167336b368bd07f3fef6ed5a6 Mon Sep 17 00:00:00 2001
From: "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com>
Date: Wed, 15 Nov 2017 17:36:02 -0800
Subject: kmemcheck: rip it out

Fix up makefiles, remove references, and git rm kmemcheck.

Link: http://lkml.kernel.org/r/20171007030159.22241-4-alexander.levin@verizon.com
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vegard Nossum <vegardno@ifi.uio.no>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Tim Hansen <devtimhansen@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt |   7 -
 Documentation/dev-tools/index.rst               |   1 -
 Documentation/dev-tools/kmemcheck.rst           | 733 ------------------------
 MAINTAINERS                                     |  10 -
 arch/x86/Kconfig                                |   3 +-
 arch/x86/include/asm/kmemcheck.h                |  42 --
 arch/x86/include/asm/string_32.h                |   9 -
 arch/x86/include/asm/string_64.h                |   8 -
 arch/x86/kernel/cpu/intel.c                     |  15 -
 arch/x86/mm/Makefile                            |   2 -
 arch/x86/mm/init.c                              |   5 +-
 arch/x86/mm/kmemcheck/Makefile                  |   1 -
 arch/x86/mm/kmemcheck/error.c                   | 227 --------
 arch/x86/mm/kmemcheck/error.h                   |  15 -
 arch/x86/mm/kmemcheck/kmemcheck.c               | 658 ---------------------
 arch/x86/mm/kmemcheck/opcode.c                  | 106 ----
 arch/x86/mm/kmemcheck/opcode.h                  |   9 -
 arch/x86/mm/kmemcheck/pte.c                     |  22 -
 arch/x86/mm/kmemcheck/pte.h                     |  10 -
 arch/x86/mm/kmemcheck/selftest.c                |  70 ---
 arch/x86/mm/kmemcheck/selftest.h                |   6 -
 arch/x86/mm/kmemcheck/shadow.c                  | 173 ------
 arch/x86/mm/kmemcheck/shadow.h                  |  18 -
 include/linux/interrupt.h                       |  15 -
 include/linux/kmemcheck.h                       | 171 ------
 kernel/softirq.c                                |  10 -
 kernel/sysctl.c                                 |  10 -
 lib/Kconfig.debug                               |   6 +-
 lib/Kconfig.kmemcheck                           |  94 ---
 mm/Kconfig.debug                                |   1 -
 mm/Makefile                                     |   2 -
 mm/kmemcheck.c                                  | 125 ----
 mm/slub.c                                       |   5 +-
 scripts/kernel-doc                              |   2 -
 tools/include/linux/kmemcheck.h                 |   8 -
 35 files changed, 7 insertions(+), 2592 deletions(-)
 delete mode 100644 Documentation/dev-tools/kmemcheck.rst
 delete mode 100644 arch/x86/mm/kmemcheck/Makefile
 delete mode 100644 arch/x86/mm/kmemcheck/kmemcheck.c
 delete mode 100644 arch/x86/mm/kmemcheck/shadow.c
 delete mode 100644 lib/Kconfig.kmemcheck

(limited to 'tools')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index b74e13312fdc..00bb04972612 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1864,13 +1864,6 @@
 			Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
 			the default is off.
 
-	kmemcheck=	[X86] Boot-time kmemcheck enable/disable/one-shot mode
-			Valid arguments: 0, 1, 2
-			kmemcheck=0 (disabled)
-			kmemcheck=1 (enabled)
-			kmemcheck=2 (one-shot mode)
-			Default: 2 (one-shot mode)
-
 	kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
 			Default is 0 (don't ignore, but inject #GP)
 
diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst
index a81787cd47d7..e313925fb0fa 100644
--- a/Documentation/dev-tools/index.rst
+++ b/Documentation/dev-tools/index.rst
@@ -21,7 +21,6 @@ whole; patches welcome!
    kasan
    ubsan
    kmemleak
-   kmemcheck
    gdb-kernel-debugging
    kgdb
    kselftest
diff --git a/Documentation/dev-tools/kmemcheck.rst b/Documentation/dev-tools/kmemcheck.rst
deleted file mode 100644
index 7f3d1985de74..000000000000
--- a/Documentation/dev-tools/kmemcheck.rst
+++ /dev/null
@@ -1,733 +0,0 @@
-Getting started with kmemcheck
-==============================
-
-Vegard Nossum <vegardno@ifi.uio.no>
-
-
-Introduction
-------------
-
-kmemcheck is a debugging feature for the Linux Kernel. More specifically, it
-is a dynamic checker that detects and warns about some uses of uninitialized
-memory.
-
-Userspace programmers might be familiar with Valgrind's memcheck. The main
-difference between memcheck and kmemcheck is that memcheck works for userspace
-programs only, and kmemcheck works for the kernel only. The implementations
-are of course vastly different. Because of this, kmemcheck is not as accurate
-as memcheck, but it turns out to be good enough in practice to discover real
-programmer errors that the compiler is not able to find through static
-analysis.
-
-Enabling kmemcheck on a kernel will probably slow it down to the extent that
-the machine will not be usable for normal workloads such as e.g. an
-interactive desktop. kmemcheck will also cause the kernel to use about twice
-as much memory as normal. For this reason, kmemcheck is strictly a debugging
-feature.
-
-
-Downloading
------------
-
-As of version 2.6.31-rc1, kmemcheck is included in the mainline kernel.
-
-
-Configuring and compiling
--------------------------
-
-kmemcheck only works for the x86 (both 32- and 64-bit) platform. A number of
-configuration variables must have specific settings in order for the kmemcheck
-menu to even appear in "menuconfig". These are:
-
-- ``CONFIG_CC_OPTIMIZE_FOR_SIZE=n``
-	This option is located under "General setup" / "Optimize for size".
-
-	Without this, gcc will use certain optimizations that usually lead to
-	false positive warnings from kmemcheck. An example of this is a 16-bit
-	field in a struct, where gcc may load 32 bits, then discard the upper
-	16 bits. kmemcheck sees only the 32-bit load, and may trigger a
-	warning for the upper 16 bits (if they're uninitialized).
-
-- ``CONFIG_SLAB=y`` or ``CONFIG_SLUB=y``
-	This option is located under "General setup" / "Choose SLAB
-	allocator".
-
-- ``CONFIG_FUNCTION_TRACER=n``
-	This option is located under "Kernel hacking" / "Tracers" / "Kernel
-	Function Tracer"
-
-	When function tracing is compiled in, gcc emits a call to another
-	function at the beginning of every function. This means that when the
-	page fault handler is called, the ftrace framework will be called
-	before kmemcheck has had a chance to handle the fault. If ftrace then
-	modifies memory that was tracked by kmemcheck, the result is an
-	endless recursive page fault.
-
-- ``CONFIG_DEBUG_PAGEALLOC=n``
-	This option is located under "Kernel hacking" / "Memory Debugging"
-	/ "Debug page memory allocations".
-
-In addition, I highly recommend turning on ``CONFIG_DEBUG_INFO=y``. This is also
-located under "Kernel hacking". With this, you will be able to get line number
-information from the kmemcheck warnings, which is extremely valuable in
-debugging a problem. This option is not mandatory, however, because it slows
-down the compilation process and produces a much bigger kernel image.
-
-Now the kmemcheck menu should be visible (under "Kernel hacking" / "Memory
-Debugging" / "kmemcheck: trap use of uninitialized memory"). Here follows
-a description of the kmemcheck configuration variables:
-
-- ``CONFIG_KMEMCHECK``
-	This must be enabled in order to use kmemcheck at all...
-
-- ``CONFIG_KMEMCHECK_``[``DISABLED`` | ``ENABLED`` | ``ONESHOT``]``_BY_DEFAULT``
-	This option controls the status of kmemcheck at boot-time. "Enabled"
-	will enable kmemcheck right from the start, "disabled" will boot the
-	kernel as normal (but with the kmemcheck code compiled in, so it can
-	be enabled at run-time after the kernel has booted), and "one-shot" is
-	a special mode which will turn kmemcheck off automatically after
-	detecting the first use of uninitialized memory.
-
-	If you are using kmemcheck to actively debug a problem, then you
-	probably want to choose "enabled" here.
-
-	The one-shot mode is mostly useful in automated test setups because it
-	can prevent floods of warnings and increase the chances of the machine
-	surviving in case something is really wrong. In other cases, the one-
-	shot mode could actually be counter-productive because it would turn
-	itself off at the very first error -- in the case of a false positive
-	too -- and this would come in the way of debugging the specific
-	problem you were interested in.
-
-	If you would like to use your kernel as normal, but with a chance to
-	enable kmemcheck in case of some problem, it might be a good idea to
-	choose "disabled" here. When kmemcheck is disabled, most of the run-
-	time overhead is not incurred, and the kernel will be almost as fast
-	as normal.
-
-- ``CONFIG_KMEMCHECK_QUEUE_SIZE``
-	Select the maximum number of error reports to store in an internal
-	(fixed-size) buffer. Since errors can occur virtually anywhere and in
-	any context, we need a temporary storage area which is guaranteed not
-	to generate any other page faults when accessed. The queue will be
-	emptied as soon as a tasklet may be scheduled. If the queue is full,
-	new error reports will be lost.
-
-	The default value of 64 is probably fine. If some code produces more
-	than 64 errors within an irqs-off section, then the code is likely to
-	produce many, many more, too, and these additional reports seldom give
-	any more information (the first report is usually the most valuable
-	anyway).
-
-	This number might have to be adjusted if you are not using serial
-	console or similar to capture the kernel log. If you are using the
-	"dmesg" command to save the log, then getting a lot of kmemcheck
-	warnings might overflow the kernel log itself, and the earlier reports
-	will get lost in that way instead. Try setting this to 10 or so on
-	such a setup.
-
-- ``CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT``
-	Select the number of shadow bytes to save along with each entry of the
-	error-report queue. These bytes indicate what parts of an allocation
-	are initialized, uninitialized, etc. and will be displayed when an
-	error is detected to help the debugging of a particular problem.
-
-	The number entered here is actually the logarithm of the number of
-	bytes that will be saved. So if you pick for example 5 here, kmemcheck
-	will save 2^5 = 32 bytes.
-
-	The default value should be fine for debugging most problems. It also
-	fits nicely within 80 columns.
-
-- ``CONFIG_KMEMCHECK_PARTIAL_OK``
-	This option (when enabled) works around certain GCC optimizations that
-	produce 32-bit reads from 16-bit variables where the upper 16 bits are
-	thrown away afterwards.
-
-	The default value (enabled) is recommended. This may of course hide
-	some real errors, but disabling it would probably produce a lot of
-	false positives.
-
-- ``CONFIG_KMEMCHECK_BITOPS_OK``
-	This option silences warnings that would be generated for bit-field
-	accesses where not all the bits are initialized at the same time. This
-	may also hide some real bugs.
-
-	This option is probably obsolete, or it should be replaced with
-	the kmemcheck-/bitfield-annotations for the code in question. The
-	default value is therefore fine.
-
-Now compile the kernel as usual.
-
-
-How to use
-----------
-
-Booting
-~~~~~~~
-
-First some information about the command-line options. There is only one
-option specific to kmemcheck, and this is called "kmemcheck". It can be used
-to override the default mode as chosen by the ``CONFIG_KMEMCHECK_*_BY_DEFAULT``
-option. Its possible settings are:
-
-- ``kmemcheck=0`` (disabled)
-- ``kmemcheck=1`` (enabled)
-- ``kmemcheck=2`` (one-shot mode)
-
-If SLUB debugging has been enabled in the kernel, it may take precedence over
-kmemcheck in such a way that the slab caches which are under SLUB debugging
-will not be tracked by kmemcheck. In order to ensure that this doesn't happen
-(even though it shouldn't by default), use SLUB's boot option ``slub_debug``,
-like this: ``slub_debug=-``
-
-In fact, this option may also be used for fine-grained control over SLUB vs.
-kmemcheck. For example, if the command line includes
-``kmemcheck=1 slub_debug=,dentry``, then SLUB debugging will be used only
-for the "dentry" slab cache, and with kmemcheck tracking all the other
-caches. This is advanced usage, however, and is not generally recommended.
-
-
-Run-time enable/disable
-~~~~~~~~~~~~~~~~~~~~~~~
-
-When the kernel has booted, it is possible to enable or disable kmemcheck at
-run-time. WARNING: This feature is still experimental and may cause false
-positive warnings to appear. Therefore, try not to use this. If you find that
-it doesn't work properly (e.g. you see an unreasonable amount of warnings), I
-will be happy to take bug reports.
-
-Use the file ``/proc/sys/kernel/kmemcheck`` for this purpose, e.g.::
-
-	$ echo 0 > /proc/sys/kernel/kmemcheck # disables kmemcheck
-
-The numbers are the same as for the ``kmemcheck=`` command-line option.
-
-
-Debugging
-~~~~~~~~~
-
-A typical report will look something like this::
-
-    WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024)
-    80000000000000000000000000000000000000000088ffff0000000000000000
-     i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
-             ^
-
-    Pid: 1856, comm: ntpdate Not tainted 2.6.29-rc5 #264 945P-A
-    RIP: 0010:[<ffffffff8104ede8>]  [<ffffffff8104ede8>] __dequeue_signal+0xc8/0x190
-    RSP: 0018:ffff88003cdf7d98  EFLAGS: 00210002
-    RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009
-    RDX: ffff88003e5d6018 RSI: ffff88003e5d6024 RDI: ffff88003cdf7e84
-    RBP: ffff88003cdf7db8 R08: ffff88003e5d6000 R09: 0000000000000000
-    R10: 0000000000000080 R11: 0000000000000000 R12: 000000000000000e
-    R13: ffff88003cdf7e78 R14: ffff88003d530710 R15: ffff88003d5a98c8
-    FS:  0000000000000000(0000) GS:ffff880001982000(0063) knlGS:00000
-    CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
-    CR2: ffff88003f806ea0 CR3: 000000003c036000 CR4: 00000000000006a0
-    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
-    DR3: 0000000000000000 DR6: 00000000ffff4ff0 DR7: 0000000000000400
-     [<ffffffff8104f04e>] dequeue_signal+0x8e/0x170
-     [<ffffffff81050bd8>] get_signal_to_deliver+0x98/0x390
-     [<ffffffff8100b87d>] do_notify_resume+0xad/0x7d0
-     [<ffffffff8100c7b5>] int_signal+0x12/0x17
-     [<ffffffffffffffff>] 0xffffffffffffffff
-
-The single most valuable information in this report is the RIP (or EIP on 32-
-bit) value. This will help us pinpoint exactly which instruction that caused
-the warning.
-
-If your kernel was compiled with ``CONFIG_DEBUG_INFO=y``, then all we have to do
-is give this address to the addr2line program, like this::
-
-	$ addr2line -e vmlinux -i ffffffff8104ede8
-	arch/x86/include/asm/string_64.h:12
-	include/asm-generic/siginfo.h:287
-	kernel/signal.c:380
-	kernel/signal.c:410
-
-The "``-e vmlinux``" tells addr2line which file to look in. **IMPORTANT:**
-This must be the vmlinux of the kernel that produced the warning in the
-first place! If not, the line number information will almost certainly be
-wrong.
-
-The "``-i``" tells addr2line to also print the line numbers of inlined
-functions.  In this case, the flag was very important, because otherwise,
-it would only have printed the first line, which is just a call to
-``memcpy()``, which could be called from a thousand places in the kernel, and
-is therefore not very useful.  These inlined functions would not show up in
-the stack trace above, simply because the kernel doesn't load the extra
-debugging information. This technique can of course be used with ordinary
-kernel oopses as well.
-
-In this case, it's the caller of ``memcpy()`` that is interesting, and it can be
-found in ``include/asm-generic/siginfo.h``, line 287::
-
-    281 static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
-    282 {
-    283         if (from->si_code < 0)
-    284                 memcpy(to, from, sizeof(*to));
-    285         else
-    286                 /* _sigchld is currently the largest know union member */
-    287                 memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld));
-    288 }
-
-Since this was a read (kmemcheck usually warns about reads only, though it can
-warn about writes to unallocated or freed memory as well), it was probably the
-"from" argument which contained some uninitialized bytes. Following the chain
-of calls, we move upwards to see where "from" was allocated or initialized,
-``kernel/signal.c``, line 380::
-
-    359 static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
-    360 {
-    ...
-    367         list_for_each_entry(q, &list->list, list) {
-    368                 if (q->info.si_signo == sig) {
-    369                         if (first)
-    370                                 goto still_pending;
-    371                         first = q;
-    ...
-    377         if (first) {
-    378 still_pending:
-    379                 list_del_init(&first->list);
-    380                 copy_siginfo(info, &first->info);
-    381                 __sigqueue_free(first);
-    ...
-    392         }
-    393 }
-
-Here, it is ``&first->info`` that is being passed on to ``copy_siginfo()``. The
-variable ``first`` was found on a list -- passed in as the second argument to
-``collect_signal()``. We  continue our journey through the stack, to figure out
-where the item on "list" was allocated or initialized. We move to line 410::
-
-    395 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
-    396                         siginfo_t *info)
-    397 {
-    ...
-    410                 collect_signal(sig, pending, info);
-    ...
-    414 }
-
-Now we need to follow the ``pending`` pointer, since that is being passed on to
-``collect_signal()`` as ``list``. At this point, we've run out of lines from the
-"addr2line" output. Not to worry, we just paste the next addresses from the
-kmemcheck stack dump, i.e.::
-
-     [<ffffffff8104f04e>] dequeue_signal+0x8e/0x170
-     [<ffffffff81050bd8>] get_signal_to_deliver+0x98/0x390
-     [<ffffffff8100b87d>] do_notify_resume+0xad/0x7d0
-     [<ffffffff8100c7b5>] int_signal+0x12/0x17
-
-	$ addr2line -e vmlinux -i ffffffff8104f04e ffffffff81050bd8 \
-		ffffffff8100b87d ffffffff8100c7b5
-	kernel/signal.c:446
-	kernel/signal.c:1806
-	arch/x86/kernel/signal.c:805
-	arch/x86/kernel/signal.c:871
-	arch/x86/kernel/entry_64.S:694
-
-Remember that since these addresses were found on the stack and not as the
-RIP value, they actually point to the _next_ instruction (they are return
-addresses). This becomes obvious when we look at the code for line 446::
-
-    422 int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
-    423 {
-    ...
-    431                 signr = __dequeue_signal(&tsk->signal->shared_pending,
-    432						 mask, info);
-    433			/*
-    434			 * itimer signal ?
-    435			 *
-    436			 * itimers are process shared and we restart periodic
-    437			 * itimers in the signal delivery path to prevent DoS
-    438			 * attacks in the high resolution timer case. This is
-    439			 * compliant with the old way of self restarting
-    440			 * itimers, as the SIGALRM is a legacy signal and only
-    441			 * queued once. Changing the restart behaviour to
-    442			 * restart the timer in the signal dequeue path is
-    443			 * reducing the timer noise on heavy loaded !highres
-    444			 * systems too.
-    445			 */
-    446			if (unlikely(signr == SIGALRM)) {
-    ...
-    489 }
-
-So instead of looking at 446, we should be looking at 431, which is the line
-that executes just before 446. Here we see that what we are looking for is
-``&tsk->signal->shared_pending``.
-
-Our next task is now to figure out which function that puts items on this
-``shared_pending`` list. A crude, but efficient tool, is ``git grep``::
-
-	$ git grep -n 'shared_pending' kernel/
-	...
-	kernel/signal.c:828:	pending = group ? &t->signal->shared_pending : &t->pending;
-	kernel/signal.c:1339:	pending = group ? &t->signal->shared_pending : &t->pending;
-	...
-
-There were more results, but none of them were related to list operations,
-and these were the only assignments. We inspect the line numbers more closely
-and find that this is indeed where items are being added to the list::
-
-    816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
-    817				int group)
-    818 {
-    ...
-    828		pending = group ? &t->signal->shared_pending : &t->pending;
-    ...
-    851		q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
-    852						     (is_si_special(info) ||
-    853						      info->si_code >= 0)));
-    854		if (q) {
-    855			list_add_tail(&q->list, &pending->list);
-    ...
-    890 }
-
-and::
-
-    1309 int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
-    1310 {
-    ....
-    1339	 pending = group ? &t->signal->shared_pending : &t->pending;
-    1340	 list_add_tail(&q->list, &pending->list);
-    ....
-    1347 }
-
-In the first case, the list element we are looking for, ``q``, is being
-returned from the function ``__sigqueue_alloc()``, which looks like an
-allocation function.  Let's take a look at it::
-
-    187 static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
-    188						 int override_rlimit)
-    189 {
-    190		struct sigqueue *q = NULL;
-    191		struct user_struct *user;
-    192
-    193		/*
-    194		 * We won't get problems with the target's UID changing under us
-    195		 * because changing it requires RCU be used, and if t != current, the
-    196		 * caller must be holding the RCU readlock (by way of a spinlock) and
-    197		 * we use RCU protection here
-    198		 */
-    199		user = get_uid(__task_cred(t)->user);
-    200		atomic_inc(&user->sigpending);
-    201		if (override_rlimit ||
-    202		    atomic_read(&user->sigpending) <=
-    203				t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
-    204			q = kmem_cache_alloc(sigqueue_cachep, flags);
-    205		if (unlikely(q == NULL)) {
-    206			atomic_dec(&user->sigpending);
-    207			free_uid(user);
-    208		} else {
-    209			INIT_LIST_HEAD(&q->list);
-    210			q->flags = 0;
-    211			q->user = user;
-    212		}
-    213
-    214		return q;
-    215 }
-
-We see that this function initializes ``q->list``, ``q->flags``, and
-``q->user``. It seems that now is the time to look at the definition of
-``struct sigqueue``, e.g.::
-
-    14 struct sigqueue {
-    15	       struct list_head list;
-    16	       int flags;
-    17	       siginfo_t info;
-    18	       struct user_struct *user;
-    19 };
-
-And, you might remember, it was a ``memcpy()`` on ``&first->info`` that
-caused the warning, so this makes perfect sense. It also seems reasonable
-to assume that it is the caller of ``__sigqueue_alloc()`` that has the
-responsibility of filling out (initializing) this member.
-
-But just which fields of the struct were uninitialized? Let's look at
-kmemcheck's report again::
-
-    WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024)
-    80000000000000000000000000000000000000000088ffff0000000000000000
-     i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
-	     ^
-
-These first two lines are the memory dump of the memory object itself, and
-the shadow bytemap, respectively. The memory object itself is in this case
-``&first->info``. Just beware that the start of this dump is NOT the start
-of the object itself! The position of the caret (^) corresponds with the
-address of the read (ffff88003e4a2024).
-
-The shadow bytemap dump legend is as follows:
-
-- i: initialized
-- u: uninitialized
-- a: unallocated (memory has been allocated by the slab layer, but has not
-  yet been handed off to anybody)
-- f: freed (memory has been allocated by the slab layer, but has been freed
-  by the previous owner)
-
-In order to figure out where (relative to the start of the object) the
-uninitialized memory was located, we have to look at the disassembly. For
-that, we'll need the RIP address again::
-
-    RIP: 0010:[<ffffffff8104ede8>]  [<ffffffff8104ede8>] __dequeue_signal+0xc8/0x190
-
-	$ objdump -d --no-show-raw-insn vmlinux | grep -C 8 ffffffff8104ede8:
-	ffffffff8104edc8:	mov    %r8,0x8(%r8)
-	ffffffff8104edcc:	test   %r10d,%r10d
-	ffffffff8104edcf:	js     ffffffff8104ee88 <__dequeue_signal+0x168>
-	ffffffff8104edd5:	mov    %rax,%rdx
-	ffffffff8104edd8:	mov    $0xc,%ecx
-	ffffffff8104eddd:	mov    %r13,%rdi
-	ffffffff8104ede0:	mov    $0x30,%eax
-	ffffffff8104ede5:	mov    %rdx,%rsi
-	ffffffff8104ede8:	rep movsl %ds:(%rsi),%es:(%rdi)
-	ffffffff8104edea:	test   $0x2,%al
-	ffffffff8104edec:	je     ffffffff8104edf0 <__dequeue_signal+0xd0>
-	ffffffff8104edee:	movsw  %ds:(%rsi),%es:(%rdi)
-	ffffffff8104edf0:	test   $0x1,%al
-	ffffffff8104edf2:	je     ffffffff8104edf5 <__dequeue_signal+0xd5>
-	ffffffff8104edf4:	movsb  %ds:(%rsi),%es:(%rdi)
-	ffffffff8104edf5:	mov    %r8,%rdi
-	ffffffff8104edf8:	callq  ffffffff8104de60 <__sigqueue_free>
-
-As expected, it's the "``rep movsl``" instruction from the ``memcpy()``
-that causes the warning. We know about ``REP MOVSL`` that it uses the register
-``RCX`` to count the number of remaining iterations. By taking a look at the
-register dump again (from the kmemcheck report), we can figure out how many
-bytes were left to copy::
-
-    RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009
-
-By looking at the disassembly, we also see that ``%ecx`` is being loaded
-with the value ``$0xc`` just before (ffffffff8104edd8), so we are very
-lucky. Keep in mind that this is the number of iterations, not bytes. And
-since this is a "long" operation, we need to multiply by 4 to get the
-number of bytes. So this means that the uninitialized value was encountered
-at 4 * (0xc - 0x9) = 12 bytes from the start of the object.
-
-We can now try to figure out which field of the "``struct siginfo``" that
-was not initialized. This is the beginning of the struct::
-
-    40 typedef struct siginfo {
-    41	       int si_signo;
-    42	       int si_errno;
-    43	       int si_code;
-    44
-    45	       union {
-    ..
-    92	       } _sifields;
-    93 } siginfo_t;
-
-On 64-bit, the int is 4 bytes long, so it must the union member that has
-not been initialized. We can verify this using gdb::
-
-	$ gdb vmlinux
-	...
-	(gdb) p &((struct siginfo *) 0)->_sifields
-	$1 = (union {...} *) 0x10
-
-Actually, it seems that the union member is located at offset 0x10 -- which
-means that gcc has inserted 4 bytes of padding between the members ``si_code``
-and ``_sifields``. We can now get a fuller picture of the memory dump::
-
-		 _----------------------------=> si_code
-		/	 _--------------------=> (padding)
-	       |	/	 _------------=> _sifields(._kill._pid)
-	       |       |	/	 _----=> _sifields(._kill._uid)
-	       |       |       |	/
-	-------|-------|-------|-------|
-	80000000000000000000000000000000000000000088ffff0000000000000000
-	 i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
-
-This allows us to realize another important fact: ``si_code`` contains the
-value 0x80. Remember that x86 is little endian, so the first 4 bytes
-"80000000" are really the number 0x00000080. With a bit of research, we
-find that this is actually the constant ``SI_KERNEL`` defined in
-``include/asm-generic/siginfo.h``::
-
-    144 #define SI_KERNEL	0x80		/* sent by the kernel from somewhere	 */
-
-This macro is used in exactly one place in the x86 kernel: In ``send_signal()``
-in ``kernel/signal.c``::
-
-    816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
-    817				int group)
-    818 {
-    ...
-    828		pending = group ? &t->signal->shared_pending : &t->pending;
-    ...
-    851		q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
-    852						     (is_si_special(info) ||
-    853						      info->si_code >= 0)));
-    854		if (q) {
-    855			list_add_tail(&q->list, &pending->list);
-    856			switch ((unsigned long) info) {
-    ...
-    865			case (unsigned long) SEND_SIG_PRIV:
-    866				q->info.si_signo = sig;
-    867				q->info.si_errno = 0;
-    868				q->info.si_code = SI_KERNEL;
-    869				q->info.si_pid = 0;
-    870				q->info.si_uid = 0;
-    871				break;
-    ...
-    890 }
-
-Not only does this match with the ``.si_code`` member, it also matches the place
-we found earlier when looking for where siginfo_t objects are enqueued on the
-``shared_pending`` list.
-
-So to sum up: It seems that it is the padding introduced by the compiler
-between two struct fields that is uninitialized, and this gets reported when
-we do a ``memcpy()`` on the struct. This means that we have identified a false
-positive warning.
-
-Normally, kmemcheck will not report uninitialized accesses in ``memcpy()`` calls
-when both the source and destination addresses are tracked. (Instead, we copy
-the shadow bytemap as well). In this case, the destination address clearly
-was not tracked. We can dig a little deeper into the stack trace from above::
-
-	arch/x86/kernel/signal.c:805
-	arch/x86/kernel/signal.c:871
-	arch/x86/kernel/entry_64.S:694
-
-And we clearly see that the destination siginfo object is located on the
-stack::
-
-    782 static void do_signal(struct pt_regs *regs)
-    783 {
-    784		struct k_sigaction ka;
-    785		siginfo_t info;
-    ...
-    804		signr = get_signal_to_deliver(&info, &ka, regs, NULL);
-    ...
-    854 }
-
-And this ``&info`` is what eventually gets passed to ``copy_siginfo()`` as the
-destination argument.
-
-Now, even though we didn't find an actual error here, the example is still a
-good one, because it shows how one would go about to find out what the report
-was all about.
-
-
-Annotating false positives
-~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-There are a few different ways to make annotations in the source code that
-will keep kmemcheck from checking and reporting certain allocations. Here
-they are:
-
-- ``__GFP_NOTRACK_FALSE_POSITIVE``
-	This flag can be passed to ``kmalloc()`` or ``kmem_cache_alloc()``
-	(therefore also to other functions that end up calling one of
-	these) to indicate that the allocation should not be tracked
-	because it would lead to a false positive report. This is a "big
-	hammer" way of silencing kmemcheck; after all, even if the false
-	positive pertains to particular field in a struct, for example, we
-	will now lose the ability to find (real) errors in other parts of
-	the same struct.
-
-	Example::
-
-	    /* No warnings will ever trigger on accessing any part of x */
-	    x = kmalloc(sizeof *x, GFP_KERNEL | __GFP_NOTRACK_FALSE_POSITIVE);
-
-- ``kmemcheck_bitfield_begin(name)``/``kmemcheck_bitfield_end(name)`` and
-	``kmemcheck_annotate_bitfield(ptr, name)``
-	The first two of these three macros can be used inside struct
-	definitions to signal, respectively, the beginning and end of a
-	bitfield. Additionally, this will assign the bitfield a name, which
-	is given as an argument to the macros.
-
-	Having used these markers, one can later use
-	kmemcheck_annotate_bitfield() at the point of allocation, to indicate
-	which parts of the allocation is part of a bitfield.
-
-	Example::
-
-	    struct foo {
-		int x;
-
-		kmemcheck_bitfield_begin(flags);
-		int flag_a:1;
-		int flag_b:1;
-		kmemcheck_bitfield_end(flags);
-
-		int y;
-	    };
-
-	    struct foo *x = kmalloc(sizeof *x);
-
-	    /* No warnings will trigger on accessing the bitfield of x */
-	    kmemcheck_annotate_bitfield(x, flags);
-
-	Note that ``kmemcheck_annotate_bitfield()`` can be used even before the
-	return value of ``kmalloc()`` is checked -- in other words, passing NULL
-	as the first argument is legal (and will do nothing).
-
-
-Reporting errors
-----------------
-
-As we have seen, kmemcheck will produce false positive reports. Therefore, it
-is not very wise to blindly post kmemcheck warnings to mailing lists and
-maintainers. Instead, I encourage maintainers and developers to find errors
-in their own code. If you get a warning, you can try to work around it, try
-to figure out if it's a real error or not, or simply ignore it. Most
-developers know their own code and will quickly and efficiently determine the
-root cause of a kmemcheck report. This is therefore also the most efficient
-way to work with kmemcheck.
-
-That said, we (the kmemcheck maintainers) will always be on the lookout for
-false positives that we can annotate and silence. So whatever you find,
-please drop us a note privately! Kernel configs and steps to reproduce (if
-available) are of course a great help too.
-
-Happy hacking!
-
-
-Technical description
----------------------
-
-kmemcheck works by marking memory pages non-present. This means that whenever
-somebody attempts to access the page, a page fault is generated. The page
-fault handler notices that the page was in fact only hidden, and so it calls
-on the kmemcheck code to make further investigations.
-
-When the investigations are completed, kmemcheck "shows" the page by marking
-it present (as it would be under normal circumstances). This way, the
-interrupted code can continue as usual.
-
-But after the instruction has been executed, we should hide the page again, so
-that we can catch the next access too! Now kmemcheck makes use of a debugging
-feature of the processor, namely single-stepping. When the processor has
-finished the one instruction that generated the memory access, a debug
-exception is raised. From here, we simply hide the page again and continue
-execution, this time with the single-stepping feature turned off.
-
-kmemcheck requires some assistance from the memory allocator in order to work.
-The memory allocator needs to
-
-  1. Tell kmemcheck about newly allocated pages and pages that are about to
-     be freed. This allows kmemcheck to set up and tear down the shadow memory
-     for the pages in question. The shadow memory stores the status of each
-     byte in the allocation proper, e.g. whether it is initialized or
-     uninitialized.
-
-  2. Tell kmemcheck which parts of memory should be marked uninitialized.
-     There are actually a few more states, such as "not yet allocated" and
-     "recently freed".
-
-If a slab cache is set up using the SLAB_NOTRACK flag, it will never return
-memory that can take page faults because of kmemcheck.
-
-If a slab cache is NOT set up using the SLAB_NOTRACK flag, callers can still
-request memory with the __GFP_NOTRACK or __GFP_NOTRACK_FALSE_POSITIVE flags.
-This does not prevent the page faults from occurring, however, but marks the
-object in question as being initialized so that no warnings will ever be
-produced for this object.
-
-Currently, the SLAB and SLUB allocators are supported by kmemcheck.
diff --git a/MAINTAINERS b/MAINTAINERS
index 7e9c887ad951..ac814d3dd1c1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7688,16 +7688,6 @@ F:	include/linux/kdb.h
 F:	include/linux/kgdb.h
 F:	kernel/debug/
 
-KMEMCHECK
-M:	Vegard Nossum <vegardno@ifi.uio.no>
-M:	Pekka Enberg <penberg@kernel.org>
-S:	Maintained
-F:	Documentation/dev-tools/kmemcheck.rst
-F:	arch/x86/include/asm/kmemcheck.h
-F:	arch/x86/mm/kmemcheck/
-F:	include/linux/kmemcheck.h
-F:	mm/kmemcheck.c
-
 KMEMLEAK
 M:	Catalin Marinas <catalin.marinas@arm.com>
 S:	Maintained
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f08977d82ca0..cb678192da4a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -112,7 +112,6 @@ config X86
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if X86_64 && SPARSEMEM_VMEMMAP
 	select HAVE_ARCH_KGDB
-	select HAVE_ARCH_KMEMCHECK
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT
 	select HAVE_ARCH_COMPAT_MMAP_BASES	if MMU && COMPAT
@@ -1430,7 +1429,7 @@ config ARCH_DMA_ADDR_T_64BIT
 
 config X86_DIRECT_GBPAGES
 	def_bool y
-	depends on X86_64 && !DEBUG_PAGEALLOC && !KMEMCHECK
+	depends on X86_64 && !DEBUG_PAGEALLOC
 	---help---
 	  Certain kernel features effectively disable kernel
 	  linear 1 GB mappings (even if the CPU otherwise
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
index 945a0337fbcf..ea32a7d3cf1b 100644
--- a/arch/x86/include/asm/kmemcheck.h
+++ b/arch/x86/include/asm/kmemcheck.h
@@ -1,43 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_X86_KMEMCHECK_H
-#define ASM_X86_KMEMCHECK_H
-
-#include <linux/types.h>
-#include <asm/ptrace.h>
-
-#ifdef CONFIG_KMEMCHECK
-bool kmemcheck_active(struct pt_regs *regs);
-
-void kmemcheck_show(struct pt_regs *regs);
-void kmemcheck_hide(struct pt_regs *regs);
-
-bool kmemcheck_fault(struct pt_regs *regs,
-	unsigned long address, unsigned long error_code);
-bool kmemcheck_trap(struct pt_regs *regs);
-#else
-static inline bool kmemcheck_active(struct pt_regs *regs)
-{
-	return false;
-}
-
-static inline void kmemcheck_show(struct pt_regs *regs)
-{
-}
-
-static inline void kmemcheck_hide(struct pt_regs *regs)
-{
-}
-
-static inline bool kmemcheck_fault(struct pt_regs *regs,
-	unsigned long address, unsigned long error_code)
-{
-	return false;
-}
-
-static inline bool kmemcheck_trap(struct pt_regs *regs)
-{
-	return false;
-}
-#endif /* CONFIG_KMEMCHECK */
-
-#endif
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 076502241eae..55d392c6bd29 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -179,8 +179,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
  *	No 3D Now!
  */
 
-#ifndef CONFIG_KMEMCHECK
-
 #if (__GNUC__ >= 4)
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 #else
@@ -189,13 +187,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
 	 ? __constant_memcpy((t), (f), (n))	\
 	 : __memcpy((t), (f), (n)))
 #endif
-#else
-/*
- * kmemcheck becomes very happy if we use the REP instructions unconditionally,
- * because it means that we know both memory operands in advance.
- */
-#define memcpy(t, f, n) __memcpy((t), (f), (n))
-#endif
 
 #endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 0b1b4445f4c5..533f74c300c2 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -33,7 +33,6 @@ extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #ifndef CONFIG_FORTIFY_SOURCE
-#ifndef CONFIG_KMEMCHECK
 #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4
 #define memcpy(dst, src, len)					\
 ({								\
@@ -46,13 +45,6 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 	__ret;							\
 })
 #endif
-#else
-/*
- * kmemcheck becomes very happy if we use the REP instructions unconditionally,
- * because it means that we know both memory operands in advance.
- */
-#define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
-#endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMSET
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b720dacac051..b1af22073e28 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -187,21 +187,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86 == 6 && c->x86_model < 15)
 		clear_cpu_cap(c, X86_FEATURE_PAT);
 
-#ifdef CONFIG_KMEMCHECK
-	/*
-	 * P4s have a "fast strings" feature which causes single-
-	 * stepping REP instructions to only generate a #DB on
-	 * cache-line boundaries.
-	 *
-	 * Ingo Molnar reported a Pentium D (model 6) and a Xeon
-	 * (model 2) with the same problem.
-	 */
-	if (c->x86 == 15)
-		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
-				  MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
-			pr_info("kmemcheck: Disabling fast string operations\n");
-#endif
-
 	/*
 	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
 	 * clear the fast string and enhanced fast string CPU capabilities.
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 7ba7f3d7f477..8e13b8cc6bed 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -29,8 +29,6 @@ obj-$(CONFIG_X86_PTDUMP)	+= debug_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
-obj-$(CONFIG_KMEMCHECK)		+= kmemcheck/
-
 KASAN_SANITIZE_kasan_init_$(BITS).o := n
 obj-$(CONFIG_KASAN)		+= kasan_init_$(BITS).o
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ef94620ceb8a..6fdf91ef130a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -163,12 +163,11 @@ static int page_size_mask;
 static void __init probe_page_size_mask(void)
 {
 	/*
-	 * For CONFIG_KMEMCHECK or pagealloc debugging, identity mapping will
-	 * use small pages.
+	 * For pagealloc debugging, identity mapping will use small pages.
 	 * This will simplify cpa(), which otherwise needs to support splitting
 	 * large pages into small in interrupt context, etc.
 	 */
-	if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled() && !IS_ENABLED(CONFIG_KMEMCHECK))
+	if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled())
 		page_size_mask |= 1 << PG_LEVEL_2M;
 	else
 		direct_gbpages = 0;
diff --git a/arch/x86/mm/kmemcheck/Makefile b/arch/x86/mm/kmemcheck/Makefile
deleted file mode 100644
index 520b3bce4095..000000000000
--- a/arch/x86/mm/kmemcheck/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y := error.o kmemcheck.o opcode.o pte.o selftest.o shadow.o
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index 872ec4159a68..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -1,228 +1 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/interrupt.h>
-#include <linux/kdebug.h>
-#include <linux/kmemcheck.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/stacktrace.h>
-#include <linux/string.h>
-
-#include "error.h"
-#include "shadow.h"
-
-enum kmemcheck_error_type {
-	KMEMCHECK_ERROR_INVALID_ACCESS,
-	KMEMCHECK_ERROR_BUG,
-};
-
-#define SHADOW_COPY_SIZE (1 << CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT)
-
-struct kmemcheck_error {
-	enum kmemcheck_error_type type;
-
-	union {
-		/* KMEMCHECK_ERROR_INVALID_ACCESS */
-		struct {
-			/* Kind of access that caused the error */
-			enum kmemcheck_shadow state;
-			/* Address and size of the erroneous read */
-			unsigned long	address;
-			unsigned int	size;
-		};
-	};
-
-	struct pt_regs		regs;
-	struct stack_trace	trace;
-	unsigned long		trace_entries[32];
-
-	/* We compress it to a char. */
-	unsigned char		shadow_copy[SHADOW_COPY_SIZE];
-	unsigned char		memory_copy[SHADOW_COPY_SIZE];
-};
-
-/*
- * Create a ring queue of errors to output. We can't call printk() directly
- * from the kmemcheck traps, since this may call the console drivers and
- * result in a recursive fault.
- */
-static struct kmemcheck_error error_fifo[CONFIG_KMEMCHECK_QUEUE_SIZE];
-static unsigned int error_count;
-static unsigned int error_rd;
-static unsigned int error_wr;
-static unsigned int error_missed_count;
-
-static struct kmemcheck_error *error_next_wr(void)
-{
-	struct kmemcheck_error *e;
-
-	if (error_count == ARRAY_SIZE(error_fifo)) {
-		++error_missed_count;
-		return NULL;
-	}
-
-	e = &error_fifo[error_wr];
-	if (++error_wr == ARRAY_SIZE(error_fifo))
-		error_wr = 0;
-	++error_count;
-	return e;
-}
-
-static struct kmemcheck_error *error_next_rd(void)
-{
-	struct kmemcheck_error *e;
-
-	if (error_count == 0)
-		return NULL;
-
-	e = &error_fifo[error_rd];
-	if (++error_rd == ARRAY_SIZE(error_fifo))
-		error_rd = 0;
-	--error_count;
-	return e;
-}
-
-void kmemcheck_error_recall(void)
-{
-	static const char *desc[] = {
-		[KMEMCHECK_SHADOW_UNALLOCATED]		= "unallocated",
-		[KMEMCHECK_SHADOW_UNINITIALIZED]	= "uninitialized",
-		[KMEMCHECK_SHADOW_INITIALIZED]		= "initialized",
-		[KMEMCHECK_SHADOW_FREED]		= "freed",
-	};
-
-	static const char short_desc[] = {
-		[KMEMCHECK_SHADOW_UNALLOCATED]		= 'a',
-		[KMEMCHECK_SHADOW_UNINITIALIZED]	= 'u',
-		[KMEMCHECK_SHADOW_INITIALIZED]		= 'i',
-		[KMEMCHECK_SHADOW_FREED]		= 'f',
-	};
-
-	struct kmemcheck_error *e;
-	unsigned int i;
-
-	e = error_next_rd();
-	if (!e)
-		return;
-
-	switch (e->type) {
-	case KMEMCHECK_ERROR_INVALID_ACCESS:
-		printk(KERN_WARNING "WARNING: kmemcheck: Caught %d-bit read from %s memory (%p)\n",
-			8 * e->size, e->state < ARRAY_SIZE(desc) ?
-				desc[e->state] : "(invalid shadow state)",
-			(void *) e->address);
-
-		printk(KERN_WARNING);
-		for (i = 0; i < SHADOW_COPY_SIZE; ++i)
-			printk(KERN_CONT "%02x", e->memory_copy[i]);
-		printk(KERN_CONT "\n");
-
-		printk(KERN_WARNING);
-		for (i = 0; i < SHADOW_COPY_SIZE; ++i) {
-			if (e->shadow_copy[i] < ARRAY_SIZE(short_desc))
-				printk(KERN_CONT " %c", short_desc[e->shadow_copy[i]]);
-			else
-				printk(KERN_CONT " ?");
-		}
-		printk(KERN_CONT "\n");
-		printk(KERN_WARNING "%*c\n", 2 + 2
-			* (int) (e->address & (SHADOW_COPY_SIZE - 1)), '^');
-		break;
-	case KMEMCHECK_ERROR_BUG:
-		printk(KERN_EMERG "ERROR: kmemcheck: Fatal error\n");
-		break;
-	}
-
-	__show_regs(&e->regs, 1);
-	print_stack_trace(&e->trace, 0);
-}
-
-static void do_wakeup(unsigned long data)
-{
-	while (error_count > 0)
-		kmemcheck_error_recall();
-
-	if (error_missed_count > 0) {
-		printk(KERN_WARNING "kmemcheck: Lost %d error reports because "
-			"the queue was too small\n", error_missed_count);
-		error_missed_count = 0;
-	}
-}
-
-static DECLARE_TASKLET(kmemcheck_tasklet, &do_wakeup, 0);
-
-/*
- * Save the context of an error report.
- */
-void kmemcheck_error_save(enum kmemcheck_shadow state,
-	unsigned long address, unsigned int size, struct pt_regs *regs)
-{
-	static unsigned long prev_ip;
-
-	struct kmemcheck_error *e;
-	void *shadow_copy;
-	void *memory_copy;
-
-	/* Don't report several adjacent errors from the same EIP. */
-	if (regs->ip == prev_ip)
-		return;
-	prev_ip = regs->ip;
-
-	e = error_next_wr();
-	if (!e)
-		return;
-
-	e->type = KMEMCHECK_ERROR_INVALID_ACCESS;
-
-	e->state = state;
-	e->address = address;
-	e->size = size;
-
-	/* Save regs */
-	memcpy(&e->regs, regs, sizeof(*regs));
-
-	/* Save stack trace */
-	e->trace.nr_entries = 0;
-	e->trace.entries = e->trace_entries;
-	e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
-	e->trace.skip = 0;
-	save_stack_trace_regs(regs, &e->trace);
-
-	/* Round address down to nearest 16 bytes */
-	shadow_copy = kmemcheck_shadow_lookup(address
-		& ~(SHADOW_COPY_SIZE - 1));
-	BUG_ON(!shadow_copy);
-
-	memcpy(e->shadow_copy, shadow_copy, SHADOW_COPY_SIZE);
-
-	kmemcheck_show_addr(address);
-	memory_copy = (void *) (address & ~(SHADOW_COPY_SIZE - 1));
-	memcpy(e->memory_copy, memory_copy, SHADOW_COPY_SIZE);
-	kmemcheck_hide_addr(address);
-
-	tasklet_hi_schedule_first(&kmemcheck_tasklet);
-}
-
-/*
- * Save the context of a kmemcheck bug.
- */
-void kmemcheck_error_save_bug(struct pt_regs *regs)
-{
-	struct kmemcheck_error *e;
-
-	e = error_next_wr();
-	if (!e)
-		return;
-
-	e->type = KMEMCHECK_ERROR_BUG;
-
-	memcpy(&e->regs, regs, sizeof(*regs));
-
-	e->trace.nr_entries = 0;
-	e->trace.entries = e->trace_entries;
-	e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
-	e->trace.skip = 1;
-	save_stack_trace(&e->trace);
-
-	tasklet_hi_schedule_first(&kmemcheck_tasklet);
-}
diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h
index 39f80d7a874d..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/error.h
+++ b/arch/x86/mm/kmemcheck/error.h
@@ -1,16 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__ERROR_H
-#define ARCH__X86__MM__KMEMCHECK__ERROR_H
-
-#include <linux/ptrace.h>
-
-#include "shadow.h"
-
-void kmemcheck_error_save(enum kmemcheck_shadow state,
-	unsigned long address, unsigned int size, struct pt_regs *regs);
-
-void kmemcheck_error_save_bug(struct pt_regs *regs);
-
-void kmemcheck_error_recall(void);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
deleted file mode 100644
index 4515bae36bbe..000000000000
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ /dev/null
@@ -1,658 +0,0 @@
-/**
- * kmemcheck - a heavyweight memory checker for the linux kernel
- * Copyright (C) 2007, 2008  Vegard Nossum <vegardno@ifi.uio.no>
- * (With a lot of help from Ingo Molnar and Pekka Enberg.)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2) as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kallsyms.h>
-#include <linux/kernel.h>
-#include <linux/kmemcheck.h>
-#include <linux/mm.h>
-#include <linux/page-flags.h>
-#include <linux/percpu.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <asm/cacheflush.h>
-#include <asm/kmemcheck.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-
-#include "error.h"
-#include "opcode.h"
-#include "pte.h"
-#include "selftest.h"
-#include "shadow.h"
-
-
-#ifdef CONFIG_KMEMCHECK_DISABLED_BY_DEFAULT
-#  define KMEMCHECK_ENABLED 0
-#endif
-
-#ifdef CONFIG_KMEMCHECK_ENABLED_BY_DEFAULT
-#  define KMEMCHECK_ENABLED 1
-#endif
-
-#ifdef CONFIG_KMEMCHECK_ONESHOT_BY_DEFAULT
-#  define KMEMCHECK_ENABLED 2
-#endif
-
-int kmemcheck_enabled = KMEMCHECK_ENABLED;
-
-int __init kmemcheck_init(void)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * Limit SMP to use a single CPU. We rely on the fact that this code
-	 * runs before SMP is set up.
-	 */
-	if (setup_max_cpus > 1) {
-		printk(KERN_INFO
-			"kmemcheck: Limiting number of CPUs to 1.\n");
-		setup_max_cpus = 1;
-	}
-#endif
-
-	if (!kmemcheck_selftest()) {
-		printk(KERN_INFO "kmemcheck: self-tests failed; disabling\n");
-		kmemcheck_enabled = 0;
-		return -EINVAL;
-	}
-
-	printk(KERN_INFO "kmemcheck: Initialized\n");
-	return 0;
-}
-
-early_initcall(kmemcheck_init);
-
-/*
- * We need to parse the kmemcheck= option before any memory is allocated.
- */
-static int __init param_kmemcheck(char *str)
-{
-	int val;
-	int ret;
-
-	if (!str)
-		return -EINVAL;
-
-	ret = kstrtoint(str, 0, &val);
-	if (ret)
-		return ret;
-	kmemcheck_enabled = val;
-	return 0;
-}
-
-early_param("kmemcheck", param_kmemcheck);
-
-int kmemcheck_show_addr(unsigned long address)
-{
-	pte_t *pte;
-
-	pte = kmemcheck_pte_lookup(address);
-	if (!pte)
-		return 0;
-
-	set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
-	__flush_tlb_one(address);
-	return 1;
-}
-
-int kmemcheck_hide_addr(unsigned long address)
-{
-	pte_t *pte;
-
-	pte = kmemcheck_pte_lookup(address);
-	if (!pte)
-		return 0;
-
-	set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
-	__flush_tlb_one(address);
-	return 1;
-}
-
-struct kmemcheck_context {
-	bool busy;
-	int balance;
-
-	/*
-	 * There can be at most two memory operands to an instruction, but
-	 * each address can cross a page boundary -- so we may need up to
-	 * four addresses that must be hidden/revealed for each fault.
-	 */
-	unsigned long addr[4];
-	unsigned long n_addrs;
-	unsigned long flags;
-
-	/* Data size of the instruction that caused a fault. */
-	unsigned int size;
-};
-
-static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context);
-
-bool kmemcheck_active(struct pt_regs *regs)
-{
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
-	return data->balance > 0;
-}
-
-/* Save an address that needs to be shown/hidden */
-static void kmemcheck_save_addr(unsigned long addr)
-{
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
-	BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr));
-	data->addr[data->n_addrs++] = addr;
-}
-
-static unsigned int kmemcheck_show_all(void)
-{
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-	unsigned int i;
-	unsigned int n;
-
-	n = 0;
-	for (i = 0; i < data->n_addrs; ++i)
-		n += kmemcheck_show_addr(data->addr[i]);
-
-	return n;
-}
-
-static unsigned int kmemcheck_hide_all(void)
-{
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-	unsigned int i;
-	unsigned int n;
-
-	n = 0;
-	for (i = 0; i < data->n_addrs; ++i)
-		n += kmemcheck_hide_addr(data->addr[i]);
-
-	return n;
-}
-
-/*
- * Called from the #PF handler.
- */
-void kmemcheck_show(struct pt_regs *regs)
-{
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
-	BUG_ON(!irqs_disabled());
-
-	if (unlikely(data->balance != 0)) {
-		kmemcheck_show_all();
-		kmemcheck_error_save_bug(regs);
-		data->balance = 0;
-		return;
-	}
-
-	/*
-	 * None of the addresses actually belonged to kmemcheck. Note that
-	 * this is not an error.
-	 */
-	if (kmemcheck_show_all() == 0)
-		return;
-
-	++data->balance;
-
-	/*
-	 * The IF needs to be cleared as well, so that the faulting
-	 * instruction can run "uninterrupted". Otherwise, we might take
-	 * an interrupt and start executing that before we've had a chance
-	 * to hide the page again.
-	 *
-	 * NOTE: In the rare case of multiple faults, we must not override
-	 * the original flags:
-	 */
-	if (!(regs->flags & X86_EFLAGS_TF))
-		data->flags = regs->flags;
-
-	regs->flags |= X86_EFLAGS_TF;
-	regs->flags &= ~X86_EFLAGS_IF;
-}
-
-/*
- * Called from the #DB handler.
- */
-void kmemcheck_hide(struct pt_regs *regs)
-{
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-	int n;
-
-	BUG_ON(!irqs_disabled());
-
-	if (unlikely(data->balance != 1)) {
-		kmemcheck_show_all();
-		kmemcheck_error_save_bug(regs);
-		data->n_addrs = 0;
-		data->balance = 0;
-
-		if (!(data->flags & X86_EFLAGS_TF))
-			regs->flags &= ~X86_EFLAGS_TF;
-		if (data->flags & X86_EFLAGS_IF)
-			regs->flags |= X86_EFLAGS_IF;
-		return;
-	}
-
-	if (kmemcheck_enabled)
-		n = kmemcheck_hide_all();
-	else
-		n = kmemcheck_show_all();
-
-	if (n == 0)
-		return;
-
-	--data->balance;
-
-	data->n_addrs = 0;
-
-	if (!(data->flags & X86_EFLAGS_TF))
-		regs->flags &= ~X86_EFLAGS_TF;
-	if (data->flags & X86_EFLAGS_IF)
-		regs->flags |= X86_EFLAGS_IF;
-}
-
-void kmemcheck_show_pages(struct page *p, unsigned int n)
-{
-	unsigned int i;
-
-	for (i = 0; i < n; ++i) {
-		unsigned long address;
-		pte_t *pte;
-		unsigned int level;
-
-		address = (unsigned long) page_address(&p[i]);
-		pte = lookup_address(address, &level);
-		BUG_ON(!pte);
-		BUG_ON(level != PG_LEVEL_4K);
-
-		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
-		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_HIDDEN));
-		__flush_tlb_one(address);
-	}
-}
-
-bool kmemcheck_page_is_tracked(struct page *p)
-{
-	/* This will also check the "hidden" flag of the PTE. */
-	return kmemcheck_pte_lookup((unsigned long) page_address(p));
-}
-
-void kmemcheck_hide_pages(struct page *p, unsigned int n)
-{
-	unsigned int i;
-
-	for (i = 0; i < n; ++i) {
-		unsigned long address;
-		pte_t *pte;
-		unsigned int level;
-
-		address = (unsigned long) page_address(&p[i]);
-		pte = lookup_address(address, &level);
-		BUG_ON(!pte);
-		BUG_ON(level != PG_LEVEL_4K);
-
-		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
-		set_pte(pte, __pte(pte_val(*pte) | _PAGE_HIDDEN));
-		__flush_tlb_one(address);
-	}
-}
-
-/* Access may NOT cross page boundary */
-static void kmemcheck_read_strict(struct pt_regs *regs,
-	unsigned long addr, unsigned int size)
-{
-	void *shadow;
-	enum kmemcheck_shadow status;
-
-	shadow = kmemcheck_shadow_lookup(addr);
-	if (!shadow)
-		return;
-
-	kmemcheck_save_addr(addr);
-	status = kmemcheck_shadow_test(shadow, size);
-	if (status == KMEMCHECK_SHADOW_INITIALIZED)
-		return;
-
-	if (kmemcheck_enabled)
-		kmemcheck_error_save(status, addr, size, regs);
-
-	if (kmemcheck_enabled == 2)
-		kmemcheck_enabled = 0;
-
-	/* Don't warn about it again. */
-	kmemcheck_shadow_set(shadow, size);
-}
-
-bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
-{
-	enum kmemcheck_shadow status;
-	void *shadow;
-
-	shadow = kmemcheck_shadow_lookup(addr);
-	if (!shadow)
-		return true;
-
-	status = kmemcheck_shadow_test_all(shadow, size);
-
-	return status == KMEMCHECK_SHADOW_INITIALIZED;
-}
-
-/* Access may cross page boundary */
-static void kmemcheck_read(struct pt_regs *regs,
-	unsigned long addr, unsigned int size)
-{
-	unsigned long page = addr & PAGE_MASK;
-	unsigned long next_addr = addr + size - 1;
-	unsigned long next_page = next_addr & PAGE_MASK;
-
-	if (likely(page == next_page)) {
-		kmemcheck_read_strict(regs, addr, size);
-		return;
-	}
-
-	/*
-	 * What we do is basically to split the access across the
-	 * two pages and handle each part separately. Yes, this means
-	 * that we may now see reads that are 3 + 5 bytes, for
-	 * example (and if both are uninitialized, there will be two
-	 * reports), but it makes the code a lot simpler.
-	 */
-	kmemcheck_read_strict(regs, addr, next_page - addr);
-	kmemcheck_read_strict(regs, next_page, next_addr - next_page);
-}
-
-static void kmemcheck_write_strict(struct pt_regs *regs,
-	unsigned long addr, unsigned int size)
-{
-	void *shadow;
-
-	shadow = kmemcheck_shadow_lookup(addr);
-	if (!shadow)
-		return;
-
-	kmemcheck_save_addr(addr);
-	kmemcheck_shadow_set(shadow, size);
-}
-
-static void kmemcheck_write(struct pt_regs *regs,
-	unsigned long addr, unsigned int size)
-{
-	unsigned long page = addr & PAGE_MASK;
-	unsigned long next_addr = addr + size - 1;
-	unsigned long next_page = next_addr & PAGE_MASK;
-
-	if (likely(page == next_page)) {
-		kmemcheck_write_strict(regs, addr, size);
-		return;
-	}
-
-	/* See comment in kmemcheck_read(). */
-	kmemcheck_write_strict(regs, addr, next_page - addr);
-	kmemcheck_write_strict(regs, next_page, next_addr - next_page);
-}
-
-/*
- * Copying is hard. We have two addresses, each of which may be split across
- * a page (and each page will have different shadow addresses).
- */
-static void kmemcheck_copy(struct pt_regs *regs,
-	unsigned long src_addr, unsigned long dst_addr, unsigned int size)
-{
-	uint8_t shadow[8];
-	enum kmemcheck_shadow status;
-
-	unsigned long page;
-	unsigned long next_addr;
-	unsigned long next_page;
-
-	uint8_t *x;
-	unsigned int i;
-	unsigned int n;
-
-	BUG_ON(size > sizeof(shadow));
-
-	page = src_addr & PAGE_MASK;
-	next_addr = src_addr + size - 1;
-	next_page = next_addr & PAGE_MASK;
-
-	if (likely(page == next_page)) {
-		/* Same page */
-		x = kmemcheck_shadow_lookup(src_addr);
-		if (x) {
-			kmemcheck_save_addr(src_addr);
-			for (i = 0; i < size; ++i)
-				shadow[i] = x[i];
-		} else {
-			for (i = 0; i < size; ++i)
-				shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
-		}
-	} else {
-		n = next_page - src_addr;
-		BUG_ON(n > sizeof(shadow));
-
-		/* First page */
-		x = kmemcheck_shadow_lookup(src_addr);
-		if (x) {
-			kmemcheck_save_addr(src_addr);
-			for (i = 0; i < n; ++i)
-				shadow[i] = x[i];
-		} else {
-			/* Not tracked */
-			for (i = 0; i < n; ++i)
-				shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
-		}
-
-		/* Second page */
-		x = kmemcheck_shadow_lookup(next_page);
-		if (x) {
-			kmemcheck_save_addr(next_page);
-			for (i = n; i < size; ++i)
-				shadow[i] = x[i - n];
-		} else {
-			/* Not tracked */
-			for (i = n; i < size; ++i)
-				shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
-		}
-	}
-
-	page = dst_addr & PAGE_MASK;
-	next_addr = dst_addr + size - 1;
-	next_page = next_addr & PAGE_MASK;
-
-	if (likely(page == next_page)) {
-		/* Same page */
-		x = kmemcheck_shadow_lookup(dst_addr);
-		if (x) {
-			kmemcheck_save_addr(dst_addr);
-			for (i = 0; i < size; ++i) {
-				x[i] = shadow[i];
-				shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
-			}
-		}
-	} else {
-		n = next_page - dst_addr;
-		BUG_ON(n > sizeof(shadow));
-
-		/* First page */
-		x = kmemcheck_shadow_lookup(dst_addr);
-		if (x) {
-			kmemcheck_save_addr(dst_addr);
-			for (i = 0; i < n; ++i) {
-				x[i] = shadow[i];
-				shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
-			}
-		}
-
-		/* Second page */
-		x = kmemcheck_shadow_lookup(next_page);
-		if (x) {
-			kmemcheck_save_addr(next_page);
-			for (i = n; i < size; ++i) {
-				x[i - n] = shadow[i];
-				shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
-			}
-		}
-	}
-
-	status = kmemcheck_shadow_test(shadow, size);
-	if (status == KMEMCHECK_SHADOW_INITIALIZED)
-		return;
-
-	if (kmemcheck_enabled)
-		kmemcheck_error_save(status, src_addr, size, regs);
-
-	if (kmemcheck_enabled == 2)
-		kmemcheck_enabled = 0;
-}
-
-enum kmemcheck_method {
-	KMEMCHECK_READ,
-	KMEMCHECK_WRITE,
-};
-
-static void kmemcheck_access(struct pt_regs *regs,
-	unsigned long fallback_address, enum kmemcheck_method fallback_method)
-{
-	const uint8_t *insn;
-	const uint8_t *insn_primary;
-	unsigned int size;
-
-	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
-	/* Recursive fault -- ouch. */
-	if (data->busy) {
-		kmemcheck_show_addr(fallback_address);
-		kmemcheck_error_save_bug(regs);
-		return;
-	}
-
-	data->busy = true;
-
-	insn = (const uint8_t *) regs->ip;
-	insn_primary = kmemcheck_opcode_get_primary(insn);
-
-	kmemcheck_opcode_decode(insn, &size);
-
-	switch (insn_primary[0]) {
-#ifdef CONFIG_KMEMCHECK_BITOPS_OK
-		/* AND, OR, XOR */
-		/*
-		 * Unfortunately, these instructions have to be excluded from
-		 * our regular checking since they access only some (and not
-		 * all) bits. This clears out "bogus" bitfield-access warnings.
-		 */
-	case 0x80:
-	case 0x81:
-	case 0x82:
-	case 0x83:
-		switch ((insn_primary[1] >> 3) & 7) {
-			/* OR */
-		case 1:
-			/* AND */
-		case 4:
-			/* XOR */
-		case 6:
-			kmemcheck_write(regs, fallback_address, size);
-			goto out;
-
-			/* ADD */
-		case 0:
-			/* ADC */
-		case 2:
-			/* SBB */
-		case 3:
-			/* SUB */
-		case 5:
-			/* CMP */
-		case 7:
-			break;
-		}
-		break;
-#endif
-
-		/* MOVS, MOVSB, MOVSW, MOVSD */
-	case 0xa4:
-	case 0xa5:
-		/*
-		 * These instructions are special because they take two
-		 * addresses, but we only get one page fault.
-		 */
-		kmemcheck_copy(regs, regs->si, regs->di, size);
-		goto out;
-
-		/* CMPS, CMPSB, CMPSW, CMPSD */
-	case 0xa6:
-	case 0xa7:
-		kmemcheck_read(regs, regs->si, size);
-		kmemcheck_read(regs, regs->di, size);
-		goto out;
-	}
-
-	/*
-	 * If the opcode isn't special in any way, we use the data from the
-	 * page fault handler to determine the address and type of memory
-	 * access.
-	 */
-	switch (fallback_method) {
-	case KMEMCHECK_READ:
-		kmemcheck_read(regs, fallback_address, size);
-		goto out;
-	case KMEMCHECK_WRITE:
-		kmemcheck_write(regs, fallback_address, size);
-		goto out;
-	}
-
-out:
-	data->busy = false;
-}
-
-bool kmemcheck_fault(struct pt_regs *regs, unsigned long address,
-	unsigned long error_code)
-{
-	pte_t *pte;
-
-	/*
-	 * XXX: Is it safe to assume that memory accesses from virtual 86
-	 * mode or non-kernel code segments will _never_ access kernel
-	 * memory (e.g. tracked pages)? For now, we need this to avoid
-	 * invoking kmemcheck for PnP BIOS calls.
-	 */
-	if (regs->flags & X86_VM_MASK)
-		return false;
-	if (regs->cs != __KERNEL_CS)
-		return false;
-
-	pte = kmemcheck_pte_lookup(address);
-	if (!pte)
-		return false;
-
-	WARN_ON_ONCE(in_nmi());
-
-	if (error_code & 2)
-		kmemcheck_access(regs, address, KMEMCHECK_WRITE);
-	else
-		kmemcheck_access(regs, address, KMEMCHECK_READ);
-
-	kmemcheck_show(regs);
-	return true;
-}
-
-bool kmemcheck_trap(struct pt_regs *regs)
-{
-	if (!kmemcheck_active(regs))
-		return false;
-
-	/* We're done. */
-	kmemcheck_hide(regs);
-	return true;
-}
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index df8109ddf7fe..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -1,107 +1 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/types.h>
-
-#include "opcode.h"
-
-static bool opcode_is_prefix(uint8_t b)
-{
-	return
-		/* Group 1 */
-		b == 0xf0 || b == 0xf2 || b == 0xf3
-		/* Group 2 */
-		|| b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26
-		|| b == 0x64 || b == 0x65
-		/* Group 3 */
-		|| b == 0x66
-		/* Group 4 */
-		|| b == 0x67;
-}
-
-#ifdef CONFIG_X86_64
-static bool opcode_is_rex_prefix(uint8_t b)
-{
-	return (b & 0xf0) == 0x40;
-}
-#else
-static bool opcode_is_rex_prefix(uint8_t b)
-{
-	return false;
-}
-#endif
-
-#define REX_W (1 << 3)
-
-/*
- * This is a VERY crude opcode decoder. We only need to find the size of the
- * load/store that caused our #PF and this should work for all the opcodes
- * that we care about. Moreover, the ones who invented this instruction set
- * should be shot.
- */
-void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size)
-{
-	/* Default operand size */
-	int operand_size_override = 4;
-
-	/* prefixes */
-	for (; opcode_is_prefix(*op); ++op) {
-		if (*op == 0x66)
-			operand_size_override = 2;
-	}
-
-	/* REX prefix */
-	if (opcode_is_rex_prefix(*op)) {
-		uint8_t rex = *op;
-
-		++op;
-		if (rex & REX_W) {
-			switch (*op) {
-			case 0x63:
-				*size = 4;
-				return;
-			case 0x0f:
-				++op;
-
-				switch (*op) {
-				case 0xb6:
-				case 0xbe:
-					*size = 1;
-					return;
-				case 0xb7:
-				case 0xbf:
-					*size = 2;
-					return;
-				}
-
-				break;
-			}
-
-			*size = 8;
-			return;
-		}
-	}
-
-	/* escape opcode */
-	if (*op == 0x0f) {
-		++op;
-
-		/*
-		 * This is move with zero-extend and sign-extend, respectively;
-		 * we don't have to think about 0xb6/0xbe, because this is
-		 * already handled in the conditional below.
-		 */
-		if (*op == 0xb7 || *op == 0xbf)
-			operand_size_override = 2;
-	}
-
-	*size = (*op & 1) ? operand_size_override : 1;
-}
-
-const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op)
-{
-	/* skip prefixes */
-	while (opcode_is_prefix(*op))
-		++op;
-	if (opcode_is_rex_prefix(*op))
-		++op;
-	return op;
-}
diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h
index 51a1ce94c24a..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/opcode.h
+++ b/arch/x86/mm/kmemcheck/opcode.h
@@ -1,10 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__OPCODE_H
-#define ARCH__X86__MM__KMEMCHECK__OPCODE_H
-
-#include <linux/types.h>
-
-void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size);
-const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c
index 8a03be90272a..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/pte.c
+++ b/arch/x86/mm/kmemcheck/pte.c
@@ -1,23 +1 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
-
-#include <asm/pgtable.h>
-
-#include "pte.h"
-
-pte_t *kmemcheck_pte_lookup(unsigned long address)
-{
-	pte_t *pte;
-	unsigned int level;
-
-	pte = lookup_address(address, &level);
-	if (!pte)
-		return NULL;
-	if (level != PG_LEVEL_4K)
-		return NULL;
-	if (!pte_hidden(*pte))
-		return NULL;
-
-	return pte;
-}
-
diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h
index b595612382c2..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/pte.h
+++ b/arch/x86/mm/kmemcheck/pte.h
@@ -1,11 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__PTE_H
-#define ARCH__X86__MM__KMEMCHECK__PTE_H
-
-#include <linux/mm.h>
-
-#include <asm/pgtable.h>
-
-pte_t *kmemcheck_pte_lookup(unsigned long address);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c
index 7ce0be1f99eb..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/selftest.c
+++ b/arch/x86/mm/kmemcheck/selftest.c
@@ -1,71 +1 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bug.h>
-#include <linux/kernel.h>
-
-#include "opcode.h"
-#include "selftest.h"
-
-struct selftest_opcode {
-	unsigned int expected_size;
-	const uint8_t *insn;
-	const char *desc;
-};
-
-static const struct selftest_opcode selftest_opcodes[] = {
-	/* REP MOVS */
-	{1, "\xf3\xa4", 		"rep movsb <mem8>, <mem8>"},
-	{4, "\xf3\xa5",			"rep movsl <mem32>, <mem32>"},
-
-	/* MOVZX / MOVZXD */
-	{1, "\x66\x0f\xb6\x51\xf8",	"movzwq <mem8>, <reg16>"},
-	{1, "\x0f\xb6\x51\xf8",		"movzwq <mem8>, <reg32>"},
-
-	/* MOVSX / MOVSXD */
-	{1, "\x66\x0f\xbe\x51\xf8",	"movswq <mem8>, <reg16>"},
-	{1, "\x0f\xbe\x51\xf8",		"movswq <mem8>, <reg32>"},
-
-#ifdef CONFIG_X86_64
-	/* MOVZX / MOVZXD */
-	{1, "\x49\x0f\xb6\x51\xf8",	"movzbq <mem8>, <reg64>"},
-	{2, "\x49\x0f\xb7\x51\xf8",	"movzbq <mem16>, <reg64>"},
-
-	/* MOVSX / MOVSXD */
-	{1, "\x49\x0f\xbe\x51\xf8",	"movsbq <mem8>, <reg64>"},
-	{2, "\x49\x0f\xbf\x51\xf8",	"movsbq <mem16>, <reg64>"},
-	{4, "\x49\x63\x51\xf8",		"movslq <mem32>, <reg64>"},
-#endif
-};
-
-static bool selftest_opcode_one(const struct selftest_opcode *op)
-{
-	unsigned size;
-
-	kmemcheck_opcode_decode(op->insn, &size);
-
-	if (size == op->expected_size)
-		return true;
-
-	printk(KERN_WARNING "kmemcheck: opcode %s: expected size %d, got %d\n",
-		op->desc, op->expected_size, size);
-	return false;
-}
-
-static bool selftest_opcodes_all(void)
-{
-	bool pass = true;
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(selftest_opcodes); ++i)
-		pass = pass && selftest_opcode_one(&selftest_opcodes[i]);
-
-	return pass;
-}
-
-bool kmemcheck_selftest(void)
-{
-	bool pass = true;
-
-	pass = pass && selftest_opcodes_all();
-
-	return pass;
-}
diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h
index 8d759aae453d..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/selftest.h
+++ b/arch/x86/mm/kmemcheck/selftest.h
@@ -1,7 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH_X86_MM_KMEMCHECK_SELFTEST_H
-#define ARCH_X86_MM_KMEMCHECK_SELFTEST_H
-
-bool kmemcheck_selftest(void);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
deleted file mode 100644
index c2638a7d2c10..000000000000
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ /dev/null
@@ -1,173 +0,0 @@
-#include <linux/kmemcheck.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-
-#include <asm/page.h>
-#include <asm/pgtable.h>
-
-#include "pte.h"
-#include "shadow.h"
-
-/*
- * Return the shadow address for the given address. Returns NULL if the
- * address is not tracked.
- *
- * We need to be extremely careful not to follow any invalid pointers,
- * because this function can be called for *any* possible address.
- */
-void *kmemcheck_shadow_lookup(unsigned long address)
-{
-	pte_t *pte;
-	struct page *page;
-
-	if (!virt_addr_valid(address))
-		return NULL;
-
-	pte = kmemcheck_pte_lookup(address);
-	if (!pte)
-		return NULL;
-
-	page = virt_to_page(address);
-	if (!page->shadow)
-		return NULL;
-	return page->shadow + (address & (PAGE_SIZE - 1));
-}
-
-static void mark_shadow(void *address, unsigned int n,
-	enum kmemcheck_shadow status)
-{
-	unsigned long addr = (unsigned long) address;
-	unsigned long last_addr = addr + n - 1;
-	unsigned long page = addr & PAGE_MASK;
-	unsigned long last_page = last_addr & PAGE_MASK;
-	unsigned int first_n;
-	void *shadow;
-
-	/* If the memory range crosses a page boundary, stop there. */
-	if (page == last_page)
-		first_n = n;
-	else
-		first_n = page + PAGE_SIZE - addr;
-
-	shadow = kmemcheck_shadow_lookup(addr);
-	if (shadow)
-		memset(shadow, status, first_n);
-
-	addr += first_n;
-	n -= first_n;
-
-	/* Do full-page memset()s. */
-	while (n >= PAGE_SIZE) {
-		shadow = kmemcheck_shadow_lookup(addr);
-		if (shadow)
-			memset(shadow, status, PAGE_SIZE);
-
-		addr += PAGE_SIZE;
-		n -= PAGE_SIZE;
-	}
-
-	/* Do the remaining page, if any. */
-	if (n > 0) {
-		shadow = kmemcheck_shadow_lookup(addr);
-		if (shadow)
-			memset(shadow, status, n);
-	}
-}
-
-void kmemcheck_mark_unallocated(void *address, unsigned int n)
-{
-	mark_shadow(address, n, KMEMCHECK_SHADOW_UNALLOCATED);
-}
-
-void kmemcheck_mark_uninitialized(void *address, unsigned int n)
-{
-	mark_shadow(address, n, KMEMCHECK_SHADOW_UNINITIALIZED);
-}
-
-/*
- * Fill the shadow memory of the given address such that the memory at that
- * address is marked as being initialized.
- */
-void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
-	mark_shadow(address, n, KMEMCHECK_SHADOW_INITIALIZED);
-}
-EXPORT_SYMBOL_GPL(kmemcheck_mark_initialized);
-
-void kmemcheck_mark_freed(void *address, unsigned int n)
-{
-	mark_shadow(address, n, KMEMCHECK_SHADOW_FREED);
-}
-
-void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n)
-{
-	unsigned int i;
-
-	for (i = 0; i < n; ++i)
-		kmemcheck_mark_unallocated(page_address(&p[i]), PAGE_SIZE);
-}
-
-void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n)
-{
-	unsigned int i;
-
-	for (i = 0; i < n; ++i)
-		kmemcheck_mark_uninitialized(page_address(&p[i]), PAGE_SIZE);
-}
-
-void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n)
-{
-	unsigned int i;
-
-	for (i = 0; i < n; ++i)
-		kmemcheck_mark_initialized(page_address(&p[i]), PAGE_SIZE);
-}
-
-enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
-{
-#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
-	uint8_t *x;
-	unsigned int i;
-
-	x = shadow;
-
-	/*
-	 * Make sure _some_ bytes are initialized. Gcc frequently generates
-	 * code to access neighboring bytes.
-	 */
-	for (i = 0; i < size; ++i) {
-		if (x[i] == KMEMCHECK_SHADOW_INITIALIZED)
-			return x[i];
-	}
-
-	return x[0];
-#else
-	return kmemcheck_shadow_test_all(shadow, size);
-#endif
-}
-
-enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size)
-{
-	uint8_t *x;
-	unsigned int i;
-
-	x = shadow;
-
-	/* All bytes must be initialized. */
-	for (i = 0; i < size; ++i) {
-		if (x[i] != KMEMCHECK_SHADOW_INITIALIZED)
-			return x[i];
-	}
-
-	return x[0];
-}
-
-void kmemcheck_shadow_set(void *shadow, unsigned int size)
-{
-	uint8_t *x;
-	unsigned int i;
-
-	x = shadow;
-	for (i = 0; i < size; ++i)
-		x[i] = KMEMCHECK_SHADOW_INITIALIZED;
-}
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
index 49768dc18664..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ b/arch/x86/mm/kmemcheck/shadow.h
@@ -1,19 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__SHADOW_H
-#define ARCH__X86__MM__KMEMCHECK__SHADOW_H
-
-enum kmemcheck_shadow {
-	KMEMCHECK_SHADOW_UNALLOCATED,
-	KMEMCHECK_SHADOW_UNINITIALIZED,
-	KMEMCHECK_SHADOW_INITIALIZED,
-	KMEMCHECK_SHADOW_FREED,
-};
-
-void *kmemcheck_shadow_lookup(unsigned long address);
-
-enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size);
-enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow,
-						unsigned int size);
-void kmemcheck_shadow_set(void *shadow, unsigned int size);
-
-#endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index baeb872283d9..69c238210325 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -594,21 +594,6 @@ static inline void tasklet_hi_schedule(struct tasklet_struct *t)
 		__tasklet_hi_schedule(t);
 }
 
-extern void __tasklet_hi_schedule_first(struct tasklet_struct *t);
-
-/*
- * This version avoids touching any other tasklets. Needed for kmemcheck
- * in order not to take any page faults while enqueueing this tasklet;
- * consider VERY carefully whether you really need this or
- * tasklet_hi_schedule()...
- */
-static inline void tasklet_hi_schedule_first(struct tasklet_struct *t)
-{
-	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
-		__tasklet_hi_schedule_first(t);
-}
-
-
 static inline void tasklet_disable_nosync(struct tasklet_struct *t)
 {
 	atomic_inc(&t->count);
diff --git a/include/linux/kmemcheck.h b/include/linux/kmemcheck.h
index 7b1d7bead7d9..ea32a7d3cf1b 100644
--- a/include/linux/kmemcheck.h
+++ b/include/linux/kmemcheck.h
@@ -1,172 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef LINUX_KMEMCHECK_H
-#define LINUX_KMEMCHECK_H
-
-#include <linux/mm_types.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMCHECK
-extern int kmemcheck_enabled;
-
-/* The slab-related functions. */
-void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node);
-void kmemcheck_free_shadow(struct page *page, int order);
-void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
-			  size_t size);
-void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size);
-
-void kmemcheck_pagealloc_alloc(struct page *p, unsigned int order,
-			       gfp_t gfpflags);
-
-void kmemcheck_show_pages(struct page *p, unsigned int n);
-void kmemcheck_hide_pages(struct page *p, unsigned int n);
-
-bool kmemcheck_page_is_tracked(struct page *p);
-
-void kmemcheck_mark_unallocated(void *address, unsigned int n);
-void kmemcheck_mark_uninitialized(void *address, unsigned int n);
-void kmemcheck_mark_initialized(void *address, unsigned int n);
-void kmemcheck_mark_freed(void *address, unsigned int n);
-
-void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n);
-void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n);
-void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n);
-
-int kmemcheck_show_addr(unsigned long address);
-int kmemcheck_hide_addr(unsigned long address);
-
-bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size);
-
-/*
- * Bitfield annotations
- *
- * How to use: If you have a struct using bitfields, for example
- *
- *     struct a {
- *             int x:8, y:8;
- *     };
- *
- * then this should be rewritten as
- *
- *     struct a {
- *             kmemcheck_bitfield_begin(flags);
- *             int x:8, y:8;
- *             kmemcheck_bitfield_end(flags);
- *     };
- *
- * Now the "flags_begin" and "flags_end" members may be used to refer to the
- * beginning and end, respectively, of the bitfield (and things like
- * &x.flags_begin is allowed). As soon as the struct is allocated, the bit-
- * fields should be annotated:
- *
- *     struct a *a = kmalloc(sizeof(struct a), GFP_KERNEL);
- *     kmemcheck_annotate_bitfield(a, flags);
- */
-#define kmemcheck_bitfield_begin(name)	\
-	int name##_begin[0];
-
-#define kmemcheck_bitfield_end(name)	\
-	int name##_end[0];
-
-#define kmemcheck_annotate_bitfield(ptr, name)				\
-	do {								\
-		int _n;							\
-									\
-		if (!ptr)						\
-			break;						\
-									\
-		_n = (long) &((ptr)->name##_end)			\
-			- (long) &((ptr)->name##_begin);		\
-		BUILD_BUG_ON(_n < 0);					\
-									\
-		kmemcheck_mark_initialized(&((ptr)->name##_begin), _n);	\
-	} while (0)
-
-#define kmemcheck_annotate_variable(var)				\
-	do {								\
-		kmemcheck_mark_initialized(&(var), sizeof(var));	\
-	} while (0)							\
-
-#else
-#define kmemcheck_enabled 0
-
-static inline void
-kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
-{
-}
-
-static inline void
-kmemcheck_free_shadow(struct page *page, int order)
-{
-}
-
-static inline void
-kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
-		     size_t size)
-{
-}
-
-static inline void kmemcheck_slab_free(struct kmem_cache *s, void *object,
-				       size_t size)
-{
-}
-
-static inline void kmemcheck_pagealloc_alloc(struct page *p,
-	unsigned int order, gfp_t gfpflags)
-{
-}
-
-static inline bool kmemcheck_page_is_tracked(struct page *p)
-{
-	return false;
-}
-
-static inline void kmemcheck_mark_unallocated(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_uninitialized(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_freed(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_unallocated_pages(struct page *p,
-						    unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_uninitialized_pages(struct page *p,
-						      unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_initialized_pages(struct page *p,
-						    unsigned int n)
-{
-}
-
-static inline bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
-{
-	return true;
-}
-
-#define kmemcheck_bitfield_begin(name)
-#define kmemcheck_bitfield_end(name)
-#define kmemcheck_annotate_bitfield(ptr, name)	\
-	do {					\
-	} while (0)
-
-#define kmemcheck_annotate_variable(var)	\
-	do {					\
-	} while (0)
-
-#endif /* CONFIG_KMEMCHECK */
-
-#endif /* LINUX_KMEMCHECK_H */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 662f7b1b7a78..2f5e87f1bae2 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -486,16 +486,6 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(__tasklet_hi_schedule);
 
-void __tasklet_hi_schedule_first(struct tasklet_struct *t)
-{
-	lockdep_assert_irqs_disabled();
-
-	t->next = __this_cpu_read(tasklet_hi_vec.head);
-	__this_cpu_write(tasklet_hi_vec.head, t);
-	__raise_softirq_irqoff(HI_SOFTIRQ);
-}
-EXPORT_SYMBOL(__tasklet_hi_schedule_first);
-
 static __latent_entropy void tasklet_action(struct softirq_action *a)
 {
 	struct tasklet_struct *list;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9576bd582d4a..7638e2f7fff8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -30,7 +30,6 @@
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/ctype.h>
-#include <linux/kmemcheck.h>
 #include <linux/kmemleak.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -1173,15 +1172,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one_thousand,
 	},
-#endif
-#ifdef CONFIG_KMEMCHECK
-	{
-		.procname	= "kmemcheck",
-		.data		= &kmemcheck_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #endif
 	{
 		.procname	= "panic_on_warn",
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 07ce7449765a..5402e3954659 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -504,7 +504,7 @@ config DEBUG_OBJECTS_ENABLE_DEFAULT
 
 config DEBUG_SLAB
 	bool "Debug slab memory allocations"
-	depends on DEBUG_KERNEL && SLAB && !KMEMCHECK
+	depends on DEBUG_KERNEL && SLAB
 	help
 	  Say Y here to have the kernel do limited verification on memory
 	  allocation as well as poisoning memory on free to catch use of freed
@@ -516,7 +516,7 @@ config DEBUG_SLAB_LEAK
 
 config SLUB_DEBUG_ON
 	bool "SLUB debugging on by default"
-	depends on SLUB && SLUB_DEBUG && !KMEMCHECK
+	depends on SLUB && SLUB_DEBUG
 	default n
 	help
 	  Boot with debugging on by default. SLUB boots by default with
@@ -730,8 +730,6 @@ config DEBUG_STACKOVERFLOW
 
 	  If in doubt, say "N".
 
-source "lib/Kconfig.kmemcheck"
-
 source "lib/Kconfig.kasan"
 
 endmenu # "Memory Debugging"
diff --git a/lib/Kconfig.kmemcheck b/lib/Kconfig.kmemcheck
deleted file mode 100644
index 846e039a86b4..000000000000
--- a/lib/Kconfig.kmemcheck
+++ /dev/null
@@ -1,94 +0,0 @@
-config HAVE_ARCH_KMEMCHECK
-	bool
-
-if HAVE_ARCH_KMEMCHECK
-
-menuconfig KMEMCHECK
-	bool "kmemcheck: trap use of uninitialized memory"
-	depends on DEBUG_KERNEL
-	depends on !X86_USE_3DNOW
-	depends on SLUB || SLAB
-	depends on !CC_OPTIMIZE_FOR_SIZE
-	depends on !FUNCTION_TRACER
-	select FRAME_POINTER
-	select STACKTRACE
-	default n
-	help
-	  This option enables tracing of dynamically allocated kernel memory
-	  to see if memory is used before it has been given an initial value.
-	  Be aware that this requires half of your memory for bookkeeping and
-	  will insert extra code at *every* read and write to tracked memory
-	  thus slow down the kernel code (but user code is unaffected).
-
-	  The kernel may be started with kmemcheck=0 or kmemcheck=1 to disable
-	  or enable kmemcheck at boot-time. If the kernel is started with
-	  kmemcheck=0, the large memory and CPU overhead is not incurred.
-
-choice
-	prompt "kmemcheck: default mode at boot"
-	depends on KMEMCHECK
-	default KMEMCHECK_ONESHOT_BY_DEFAULT
-	help
-	  This option controls the default behaviour of kmemcheck when the
-	  kernel boots and no kmemcheck= parameter is given.
-
-config KMEMCHECK_DISABLED_BY_DEFAULT
-	bool "disabled"
-	depends on KMEMCHECK
-
-config KMEMCHECK_ENABLED_BY_DEFAULT
-	bool "enabled"
-	depends on KMEMCHECK
-
-config KMEMCHECK_ONESHOT_BY_DEFAULT
-	bool "one-shot"
-	depends on KMEMCHECK
-	help
-	  In one-shot mode, only the first error detected is reported before
-	  kmemcheck is disabled.
-
-endchoice
-
-config KMEMCHECK_QUEUE_SIZE
-	int "kmemcheck: error queue size"
-	depends on KMEMCHECK
-	default 64
-	help
-	  Select the maximum number of errors to store in the queue. Since
-	  errors can occur virtually anywhere and in any context, we need a
-	  temporary storage area which is guarantueed not to generate any
-	  other faults. The queue will be emptied as soon as a tasklet may
-	  be scheduled. If the queue is full, new error reports will be
-	  lost.
-
-config KMEMCHECK_SHADOW_COPY_SHIFT
-	int "kmemcheck: shadow copy size (5 => 32 bytes, 6 => 64 bytes)"
-	depends on KMEMCHECK
-	range 2 8
-	default 5
-	help
-	  Select the number of shadow bytes to save along with each entry of
-	  the queue. These bytes indicate what parts of an allocation are
-	  initialized, uninitialized, etc. and will be displayed when an
-	  error is detected to help the debugging of a particular problem.
-
-config KMEMCHECK_PARTIAL_OK
-	bool "kmemcheck: allow partially uninitialized memory"
-	depends on KMEMCHECK
-	default y
-	help
-	  This option works around certain GCC optimizations that produce
-	  32-bit reads from 16-bit variables where the upper 16 bits are
-	  thrown away afterwards. This may of course also hide some real
-	  bugs.
-
-config KMEMCHECK_BITOPS_OK
-	bool "kmemcheck: allow bit-field manipulation"
-	depends on KMEMCHECK
-	default n
-	help
-	  This option silences warnings that would be generated for bit-field
-	  accesses where not all the bits are initialized at the same time.
-	  This may also hide some real bugs.
-
-endif
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 5b0adf1435de..e5e606ee5f71 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -11,7 +11,6 @@ config DEBUG_PAGEALLOC
 	bool "Debug page memory allocations"
 	depends on DEBUG_KERNEL
 	depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC
-	depends on !KMEMCHECK
 	select PAGE_EXTENSION
 	select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	---help---
diff --git a/mm/Makefile b/mm/Makefile
index 4659b93cba43..e7ebd176fb93 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -17,7 +17,6 @@ KCOV_INSTRUMENT_slub.o := n
 KCOV_INSTRUMENT_page_alloc.o := n
 KCOV_INSTRUMENT_debug-pagealloc.o := n
 KCOV_INSTRUMENT_kmemleak.o := n
-KCOV_INSTRUMENT_kmemcheck.o := n
 KCOV_INSTRUMENT_memcontrol.o := n
 KCOV_INSTRUMENT_mmzone.o := n
 KCOV_INSTRUMENT_vmstat.o := n
@@ -70,7 +69,6 @@ obj-$(CONFIG_KSM) += ksm.o
 obj-$(CONFIG_PAGE_POISONING) += page_poison.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
-obj-$(CONFIG_KMEMCHECK) += kmemcheck.o
 obj-$(CONFIG_KASAN)	+= kasan/
 obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
index b3a4d61d341c..cec594032515 100644
--- a/mm/kmemcheck.c
+++ b/mm/kmemcheck.c
@@ -1,126 +1 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/gfp.h>
-#include <linux/mm_types.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include "slab.h"
-#include <linux/kmemcheck.h>
-
-void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
-{
-	struct page *shadow;
-	int pages;
-	int i;
-
-	pages = 1 << order;
-
-	/*
-	 * With kmemcheck enabled, we need to allocate a memory area for the
-	 * shadow bits as well.
-	 */
-	shadow = alloc_pages_node(node, flags, order);
-	if (!shadow) {
-		if (printk_ratelimit())
-			pr_err("kmemcheck: failed to allocate shadow bitmap\n");
-		return;
-	}
-
-	for(i = 0; i < pages; ++i)
-		page[i].shadow = page_address(&shadow[i]);
-
-	/*
-	 * Mark it as non-present for the MMU so that our accesses to
-	 * this memory will trigger a page fault and let us analyze
-	 * the memory accesses.
-	 */
-	kmemcheck_hide_pages(page, pages);
-}
-
-void kmemcheck_free_shadow(struct page *page, int order)
-{
-	struct page *shadow;
-	int pages;
-	int i;
-
-	if (!kmemcheck_page_is_tracked(page))
-		return;
-
-	pages = 1 << order;
-
-	kmemcheck_show_pages(page, pages);
-
-	shadow = virt_to_page(page[0].shadow);
-
-	for(i = 0; i < pages; ++i)
-		page[i].shadow = NULL;
-
-	__free_pages(shadow, order);
-}
-
-void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
-			  size_t size)
-{
-	if (unlikely(!object)) /* Skip object if allocation failed */
-		return;
-
-	/*
-	 * Has already been memset(), which initializes the shadow for us
-	 * as well.
-	 */
-	if (gfpflags & __GFP_ZERO)
-		return;
-
-	/* No need to initialize the shadow of a non-tracked slab. */
-	if (s->flags & SLAB_NOTRACK)
-		return;
-
-	if (!kmemcheck_enabled || gfpflags & __GFP_NOTRACK) {
-		/*
-		 * Allow notracked objects to be allocated from
-		 * tracked caches. Note however that these objects
-		 * will still get page faults on access, they just
-		 * won't ever be flagged as uninitialized. If page
-		 * faults are not acceptable, the slab cache itself
-		 * should be marked NOTRACK.
-		 */
-		kmemcheck_mark_initialized(object, size);
-	} else if (!s->ctor) {
-		/*
-		 * New objects should be marked uninitialized before
-		 * they're returned to the called.
-		 */
-		kmemcheck_mark_uninitialized(object, size);
-	}
-}
-
-void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
-{
-	/* TODO: RCU freeing is unsupported for now; hide false positives. */
-	if (!s->ctor && !(s->flags & SLAB_TYPESAFE_BY_RCU))
-		kmemcheck_mark_freed(object, size);
-}
-
-void kmemcheck_pagealloc_alloc(struct page *page, unsigned int order,
-			       gfp_t gfpflags)
-{
-	int pages;
-
-	if (gfpflags & (__GFP_HIGHMEM | __GFP_NOTRACK))
-		return;
-
-	pages = 1 << order;
-
-	/*
-	 * NOTE: We choose to track GFP_ZERO pages too; in fact, they
-	 * can become uninitialized by copying uninitialized memory
-	 * into them.
-	 */
-
-	/* XXX: Can use zone->node for node? */
-	kmemcheck_alloc_shadow(page, order, gfpflags, -1);
-
-	if (gfpflags & __GFP_ZERO)
-		kmemcheck_mark_initialized_pages(page, pages);
-	else
-		kmemcheck_mark_uninitialized_pages(page, pages);
-}
diff --git a/mm/slub.c b/mm/slub.c
index c2c41e178acf..cfd56e5a35fb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1371,7 +1371,7 @@ static inline void *slab_free_hook(struct kmem_cache *s, void *x)
 	 * So in order to make the debug calls that expect irqs to be
 	 * disabled we need to disable interrupts temporarily.
 	 */
-#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP)
+#ifdef CONFIG_LOCKDEP
 	{
 		unsigned long flags;
 
@@ -1399,8 +1399,7 @@ static inline void slab_free_freelist_hook(struct kmem_cache *s,
  * Compiler cannot detect this function can be removed if slab_free_hook()
  * evaluates to nothing.  Thus, catch all relevant config debug options here.
  */
-#if defined(CONFIG_KMEMCHECK) ||		\
-	defined(CONFIG_LOCKDEP)	||		\
+#if defined(CONFIG_LOCKDEP)	||		\
 	defined(CONFIG_DEBUG_KMEMLEAK) ||	\
 	defined(CONFIG_DEBUG_OBJECTS_FREE) ||	\
 	defined(CONFIG_KASAN)
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 67d051edd615..7bd52b8f63d4 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -2182,8 +2182,6 @@ sub dump_struct($$) {
 	# strip comments:
 	$members =~ s/\/\*.*?\*\///gos;
 	$nested =~ s/\/\*.*?\*\///gos;
-	# strip kmemcheck_bitfield_{begin,end}.*;
-	$members =~ s/kmemcheck_bitfield_.*?;//gos;
 	# strip attributes
 	$members =~ s/__attribute__\s*\(\([a-z,_\*\s\(\)]*\)\)//i;
 	$members =~ s/__aligned\s*\([^;]*\)//gos;
diff --git a/tools/include/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h
index 2bccd2c7b897..ea32a7d3cf1b 100644
--- a/tools/include/linux/kmemcheck.h
+++ b/tools/include/linux/kmemcheck.h
@@ -1,9 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_
-#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_
-
-static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
-}
-
-#endif
-- 
cgit v1.2.3


From c7df8ad2910e965a6241b6d8f52fd122e26b0315 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@techsingularity.net>
Date: Wed, 15 Nov 2017 17:37:41 -0800
Subject: mm, truncate: do not check mapping for every page being truncated

During truncation, the mapping has already been checked for shmem and
dax so it's known that workingset_update_node is required.

This patch avoids the checks on mapping for each page being truncated.
In all other cases, a lookup helper is used to determine if
workingset_update_node() needs to be called.  The one danger is that the
API is slightly harder to use as calling workingset_update_node directly
without checking for dax or shmem mappings could lead to surprises.
However, the API rarely needs to be used and hopefully the comment is
enough to give people the hint.

sparsetruncate (tiny)
                              4.14.0-rc4             4.14.0-rc4
                             oneirq-v1r1        pickhelper-v1r1
Min          Time      141.00 (   0.00%)      140.00 (   0.71%)
1st-qrtle    Time      142.00 (   0.00%)      141.00 (   0.70%)
2nd-qrtle    Time      142.00 (   0.00%)      142.00 (   0.00%)
3rd-qrtle    Time      143.00 (   0.00%)      143.00 (   0.00%)
Max-90%      Time      144.00 (   0.00%)      144.00 (   0.00%)
Max-95%      Time      147.00 (   0.00%)      145.00 (   1.36%)
Max-99%      Time      195.00 (   0.00%)      191.00 (   2.05%)
Max          Time      230.00 (   0.00%)      205.00 (  10.87%)
Amean        Time      144.37 (   0.00%)      143.82 (   0.38%)
Stddev       Time       10.44 (   0.00%)        9.00 (  13.74%)
Coeff        Time        7.23 (   0.00%)        6.26 (  13.41%)
Best99%Amean Time      143.72 (   0.00%)      143.34 (   0.26%)
Best95%Amean Time      142.37 (   0.00%)      142.00 (   0.26%)
Best90%Amean Time      142.19 (   0.00%)      141.85 (   0.24%)
Best75%Amean Time      141.92 (   0.00%)      141.58 (   0.24%)
Best50%Amean Time      141.69 (   0.00%)      141.31 (   0.27%)
Best25%Amean Time      141.38 (   0.00%)      140.97 (   0.29%)

As you'd expect, the gain is marginal but it can be detected.  The
differences in bonnie are all within the noise which is not surprising
given the impact on the microbenchmark.

radix_tree_update_node_t is a callback for some radix operations that
optionally passes in a private field.  The only user of the callback is
workingset_update_node and as it no longer requires a mapping, the
private field is removed.

Link: http://lkml.kernel.org/r/20171018075952.10627-3-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/dax.c                              |  2 +-
 include/linux/radix-tree.h            |  7 +++----
 include/linux/swap.h                  | 13 ++++++++++++-
 lib/idr.c                             |  2 +-
 lib/radix-tree.c                      | 30 +++++++++++++-----------------
 mm/filemap.c                          |  7 ++++---
 mm/shmem.c                            |  2 +-
 mm/truncate.c                         |  2 +-
 mm/workingset.c                       | 10 ++--------
 tools/testing/radix-tree/multiorder.c |  2 +-
 10 files changed, 39 insertions(+), 38 deletions(-)

(limited to 'tools')

diff --git a/fs/dax.c b/fs/dax.c
index 9ec797424e4f..165fdfb6e508 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -565,7 +565,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 		ret = __radix_tree_lookup(page_tree, index, &node, &slot);
 		WARN_ON_ONCE(ret != entry);
 		__radix_tree_replace(page_tree, node, slot,
-				     new_entry, NULL, NULL);
+				     new_entry, NULL);
 		entry = new_entry;
 	}
 
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 567ebb5eaab0..0ca448c1cb42 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -301,18 +301,17 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
 void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *,
 					unsigned long index);
-typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *);
+typedef void (*radix_tree_update_node_t)(struct radix_tree_node *);
 void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *,
 			  void __rcu **slot, void *entry,
-			  radix_tree_update_node_t update_node, void *private);
+			  radix_tree_update_node_t update_node);
 void radix_tree_iter_replace(struct radix_tree_root *,
 		const struct radix_tree_iter *, void __rcu **slot, void *entry);
 void radix_tree_replace_slot(struct radix_tree_root *,
 			     void __rcu **slot, void *entry);
 void __radix_tree_delete_node(struct radix_tree_root *,
 			      struct radix_tree_node *,
-			      radix_tree_update_node_t update_node,
-			      void *private);
+			      radix_tree_update_node_t update_node);
 void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8b8a6f965785..454f042bcdd5 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,7 +298,18 @@ struct vma_swap_readahead {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
-void workingset_update_node(struct radix_tree_node *node, void *private);
+
+/* Do not use directly, use workingset_lookup_update */
+void workingset_update_node(struct radix_tree_node *node);
+
+/* Returns workingset_update_node() if the mapping has shadow entries. */
+#define workingset_lookup_update(mapping)				\
+({									\
+	radix_tree_update_node_t __helper = workingset_update_node;	\
+	if (dax_mapping(mapping) || shmem_mapping(mapping))		\
+		__helper = NULL;					\
+	__helper;							\
+})
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
diff --git a/lib/idr.c b/lib/idr.c
index edd9b2be1651..2593ce513a18 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -171,7 +171,7 @@ void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id)
 	if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE))
 		return ERR_PTR(-ENOENT);
 
-	__radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL, NULL);
+	__radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL);
 
 	return entry;
 }
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 8b1feca1230a..c8d55565fafa 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -677,8 +677,7 @@ out:
  *	@root		radix tree root
  */
 static inline bool radix_tree_shrink(struct radix_tree_root *root,
-				     radix_tree_update_node_t update_node,
-				     void *private)
+				     radix_tree_update_node_t update_node)
 {
 	bool shrunk = false;
 
@@ -739,7 +738,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		if (!radix_tree_is_internal_node(child)) {
 			node->slots[0] = (void __rcu *)RADIX_TREE_RETRY;
 			if (update_node)
-				update_node(node, private);
+				update_node(node);
 		}
 
 		WARN_ON_ONCE(!list_empty(&node->private_list));
@@ -752,7 +751,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 
 static bool delete_node(struct radix_tree_root *root,
 			struct radix_tree_node *node,
-			radix_tree_update_node_t update_node, void *private)
+			radix_tree_update_node_t update_node)
 {
 	bool deleted = false;
 
@@ -762,8 +761,8 @@ static bool delete_node(struct radix_tree_root *root,
 		if (node->count) {
 			if (node_to_entry(node) ==
 					rcu_dereference_raw(root->rnode))
-				deleted |= radix_tree_shrink(root, update_node,
-								private);
+				deleted |= radix_tree_shrink(root,
+								update_node);
 			return deleted;
 		}
 
@@ -1173,7 +1172,6 @@ static int calculate_count(struct radix_tree_root *root,
  * @slot:		pointer to slot in @node
  * @item:		new item to store in the slot.
  * @update_node:	callback for changing leaf nodes
- * @private:		private data to pass to @update_node
  *
  * For use with __radix_tree_lookup().  Caller must hold tree write locked
  * across slot lookup and replacement.
@@ -1181,7 +1179,7 @@ static int calculate_count(struct radix_tree_root *root,
 void __radix_tree_replace(struct radix_tree_root *root,
 			  struct radix_tree_node *node,
 			  void __rcu **slot, void *item,
-			  radix_tree_update_node_t update_node, void *private)
+			  radix_tree_update_node_t update_node)
 {
 	void *old = rcu_dereference_raw(*slot);
 	int exceptional = !!radix_tree_exceptional_entry(item) -
@@ -1201,9 +1199,9 @@ void __radix_tree_replace(struct radix_tree_root *root,
 		return;
 
 	if (update_node)
-		update_node(node, private);
+		update_node(node);
 
-	delete_node(root, node, update_node, private);
+	delete_node(root, node, update_node);
 }
 
 /**
@@ -1225,7 +1223,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 void radix_tree_replace_slot(struct radix_tree_root *root,
 			     void __rcu **slot, void *item)
 {
-	__radix_tree_replace(root, NULL, slot, item, NULL, NULL);
+	__radix_tree_replace(root, NULL, slot, item, NULL);
 }
 EXPORT_SYMBOL(radix_tree_replace_slot);
 
@@ -1242,7 +1240,7 @@ void radix_tree_iter_replace(struct radix_tree_root *root,
 				const struct radix_tree_iter *iter,
 				void __rcu **slot, void *item)
 {
-	__radix_tree_replace(root, iter->node, slot, item, NULL, NULL);
+	__radix_tree_replace(root, iter->node, slot, item, NULL);
 }
 
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
@@ -1972,7 +1970,6 @@ EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
  *	@root:		radix tree root
  *	@node:		node containing @index
  *	@update_node:	callback for changing leaf nodes
- *	@private:	private data to pass to @update_node
  *
  *	After clearing the slot at @index in @node from radix tree
  *	rooted at @root, call this function to attempt freeing the
@@ -1980,10 +1977,9 @@ EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
  */
 void __radix_tree_delete_node(struct radix_tree_root *root,
 			      struct radix_tree_node *node,
-			      radix_tree_update_node_t update_node,
-			      void *private)
+			      radix_tree_update_node_t update_node)
 {
-	delete_node(root, node, update_node, private);
+	delete_node(root, node, update_node);
 }
 
 static bool __radix_tree_delete(struct radix_tree_root *root,
@@ -2001,7 +1997,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 			node_tag_clear(root, node, tag, offset);
 
 	replace_slot(slot, NULL, node, -1, exceptional);
-	return node && delete_node(root, node, NULL, NULL);
+	return node && delete_node(root, node, NULL);
 }
 
 /**
diff --git a/mm/filemap.c b/mm/filemap.c
index a470dd8cd05b..155370fc87f2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -35,6 +35,7 @@
 #include <linux/hugetlb.h>
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
+#include <linux/shmem_fs.h>
 #include <linux/rmap.h>
 #include "internal.h"
 
@@ -134,7 +135,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 			*shadowp = p;
 	}
 	__radix_tree_replace(&mapping->page_tree, node, slot, page,
-			     workingset_update_node, mapping);
+			     workingset_lookup_update(mapping));
 	mapping->nrpages++;
 	return 0;
 }
@@ -162,7 +163,7 @@ static void page_cache_tree_delete(struct address_space *mapping,
 
 		radix_tree_clear_tags(&mapping->page_tree, node, slot);
 		__radix_tree_replace(&mapping->page_tree, node, slot, shadow,
-				     workingset_update_node, mapping);
+				workingset_lookup_update(mapping));
 	}
 
 	page->mapping = NULL;
@@ -359,7 +360,7 @@ page_cache_tree_delete_batch(struct address_space *mapping,
 		}
 		radix_tree_clear_tags(&mapping->page_tree, iter.node, slot);
 		__radix_tree_replace(&mapping->page_tree, iter.node, slot, NULL,
-				     workingset_update_node, mapping);
+				workingset_lookup_update(mapping));
 		total_pages++;
 	}
 	mapping->nrpages -= total_pages;
diff --git a/mm/shmem.c b/mm/shmem.c
index 07a1d22807be..a72f68aee6a4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -338,7 +338,7 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 	if (item != expected)
 		return -ENOENT;
 	__radix_tree_replace(&mapping->page_tree, node, pslot,
-			     replacement, NULL, NULL);
+			     replacement, NULL);
 	return 0;
 }
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 4a39a3150ee2..02a0c0466c78 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -42,7 +42,7 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
 	if (*slot != entry)
 		goto unlock;
 	__radix_tree_replace(&mapping->page_tree, node, slot, NULL,
-			     workingset_update_node, mapping);
+			     workingset_update_node);
 	mapping->nrexceptional--;
 unlock:
 	spin_unlock_irq(&mapping->tree_lock);
diff --git a/mm/workingset.c b/mm/workingset.c
index b997c9de28f6..b7d616a3bbbe 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -340,14 +340,8 @@ out:
 
 static struct list_lru shadow_nodes;
 
-void workingset_update_node(struct radix_tree_node *node, void *private)
+void workingset_update_node(struct radix_tree_node *node)
 {
-	struct address_space *mapping = private;
-
-	/* Only regular page cache has shadow entries */
-	if (dax_mapping(mapping) || shmem_mapping(mapping))
-		return;
-
 	/*
 	 * Track non-empty nodes that contain only shadow entries;
 	 * unlink those that contain pages or are being freed.
@@ -475,7 +469,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		goto out_invalid;
 	inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
 	__radix_tree_delete_node(&mapping->page_tree, node,
-				 workingset_update_node, mapping);
+				 workingset_lookup_update(mapping));
 
 out_invalid:
 	spin_unlock(&mapping->tree_lock);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 06c71178d07d..59245b3d587c 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -618,7 +618,7 @@ static void multiorder_account(void)
 	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
 	assert(node->count == node->exceptional * 2);
-	__radix_tree_replace(&tree, node, slot, NULL, NULL, NULL);
+	__radix_tree_replace(&tree, node, slot, NULL, NULL);
 	assert(node->exceptional == 0);
 
 	item_kill_tree(&tree);
-- 
cgit v1.2.3


From 453f85d43fa9ee243f0fc3ac4e1be45615301e3f Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@techsingularity.net>
Date: Wed, 15 Nov 2017 17:38:03 -0800
Subject: mm: remove __GFP_COLD

As the page free path makes no distinction between cache hot and cold
pages, there is no real useful ordering of pages in the free list that
allocation requests can take advantage of.  Juding from the users of
__GFP_COLD, it is likely that a number of them are the result of copying
other sites instead of actually measuring the impact.  Remove the
__GFP_COLD parameter which simplifies a number of paths in the page
allocator.

This is potentially controversial but bear in mind that the size of the
per-cpu pagelists versus modern cache sizes means that the whole per-cpu
list can often fit in the L3 cache.  Hence, there is only a potential
benefit for microbenchmarks that alloc/free pages in a tight loop.  It's
even worse when THP is taken into account which has little or no chance
of getting a cache-hot page as the per-cpu list is bypassed and the
zeroing of multiple pages will thrash the cache anyway.

The truncate microbenchmarks are not shown as this patch affects the
allocation path and not the free path.  A page fault microbenchmark was
tested but it showed no sigificant difference which is not surprising
given that the __GFP_COLD branches are a miniscule percentage of the
fault path.

Link: http://lkml.kernel.org/r/20171018075952.10627-9-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c         |  2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-desc.c            |  2 +-
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c     |  3 +--
 .../net/ethernet/cavium/liquidio/octeon_network.h    |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c           |  5 ++---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c  |  4 ++--
 drivers/net/ethernet/qlogic/qlge/qlge_main.c         |  3 +--
 drivers/net/ethernet/sfc/falcon/rx.c                 |  2 +-
 drivers/net/ethernet/sfc/rx.c                        |  2 +-
 drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c      |  2 +-
 drivers/net/ethernet/ti/netcp_core.c                 |  2 +-
 drivers/net/virtio_net.c                             |  1 -
 drivers/staging/lustre/lustre/mdc/mdc_request.c      |  2 +-
 fs/cachefiles/rdwr.c                                 |  6 ++----
 include/linux/gfp.h                                  |  5 -----
 include/linux/pagemap.h                              |  8 +-------
 include/linux/skbuff.h                               |  2 +-
 include/linux/slab.h                                 |  3 ---
 include/trace/events/mmflags.h                       |  1 -
 kernel/power/snapshot.c                              |  4 ++--
 mm/filemap.c                                         |  6 +++---
 mm/page_alloc.c                                      | 20 ++++++--------------
 mm/percpu-vm.c                                       |  2 +-
 net/core/skbuff.c                                    |  4 ++--
 tools/perf/builtin-kmem.c                            |  1 -
 25 files changed, 32 insertions(+), 62 deletions(-)

(limited to 'tools')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c6bd5e24005d..fbbbd8b3eb45 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -517,7 +517,7 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num)
 
 
 		rc = ena_alloc_rx_page(rx_ring, rx_info,
-				       __GFP_COLD | GFP_ATOMIC | __GFP_COMP);
+				       GFP_ATOMIC | __GFP_COMP);
 		if (unlikely(rc < 0)) {
 			netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev,
 				   "failed to alloc buffer for rx queue %d\n",
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 45d92304068e..cc1e4f820e64 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -295,7 +295,7 @@ again:
 	order = alloc_order;
 
 	/* Try to obtain pages, decreasing order if necessary */
-	gfp = GFP_ATOMIC | __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
+	gfp = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
 	while (order >= 0) {
 		pages = alloc_pages_node(node, gfp, order);
 		if (pages)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 0654e0c76bc2..519ca6534b85 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -304,8 +304,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self)
 		buff->flags = 0U;
 		buff->len = AQ_CFG_RX_FRAME_MAX;
 
-		buff->page = alloc_pages(GFP_ATOMIC | __GFP_COLD |
-					 __GFP_COMP, pages_order);
+		buff->page = alloc_pages(GFP_ATOMIC | __GFP_COMP, pages_order);
 		if (!buff->page) {
 			err = -ENOMEM;
 			goto err_exit;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index 9e36319cead6..57853eead4b5 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -195,7 +195,7 @@ static inline void
 	struct sk_buff *skb;
 	struct octeon_skb_page_info *skb_pg_info;
 
-	page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+	page = alloc_page(GFP_ATOMIC);
 	if (unlikely(!page))
 		return NULL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b97a55c827eb..ffead38cf5da 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -193,7 +193,7 @@ static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
 
 			if (mlx4_en_prepare_rx_desc(priv, ring,
 						    ring->actual_size,
-						    GFP_KERNEL | __GFP_COLD)) {
+						    GFP_KERNEL)) {
 				if (ring->actual_size < MLX4_EN_MIN_RX_SIZE) {
 					en_err(priv, "Failed to allocate enough rx buffers\n");
 					return -ENOMEM;
@@ -552,8 +552,7 @@ static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
 	do {
 		if (mlx4_en_prepare_rx_desc(priv, ring,
 					    ring->prod & ring->size_mask,
-					    GFP_ATOMIC | __GFP_COLD |
-					    __GFP_MEMALLOC))
+					    GFP_ATOMIC | __GFP_MEMALLOC))
 			break;
 		ring->prod++;
 	} while (likely(--missing));
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index e118b5f23996..ffb12dc13a5a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1185,7 +1185,7 @@ static void *nfp_net_rx_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 	} else {
 		struct page *page;
 
-		page = alloc_page(GFP_KERNEL | __GFP_COLD);
+		page = alloc_page(GFP_KERNEL);
 		frag = page ? page_address(page) : NULL;
 	}
 	if (!frag) {
@@ -1212,7 +1212,7 @@ static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 	} else {
 		struct page *page;
 
-		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		page = alloc_page(GFP_ATOMIC);
 		frag = page ? page_address(page) : NULL;
 	}
 	if (!frag) {
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 29fea74bff2e..7b97a9969046 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1092,8 +1092,7 @@ static int ql_get_next_chunk(struct ql_adapter *qdev, struct rx_ring *rx_ring,
 {
 	if (!rx_ring->pg_chunk.page) {
 		u64 map;
-		rx_ring->pg_chunk.page = alloc_pages(__GFP_COLD | __GFP_COMP |
-						GFP_ATOMIC,
+		rx_ring->pg_chunk.page = alloc_pages(__GFP_COMP | GFP_ATOMIC,
 						qdev->lbq_buf_order);
 		if (unlikely(!rx_ring->pg_chunk.page)) {
 			netif_err(qdev, drv, qdev->ndev,
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 6a8406dc0c2b..91097aea6c41 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -163,7 +163,7 @@ static int ef4_init_rx_buffers(struct ef4_rx_queue *rx_queue, bool atomic)
 	do {
 		page = ef4_reuse_page(rx_queue);
 		if (page == NULL) {
-			page = alloc_pages(__GFP_COLD | __GFP_COMP |
+			page = alloc_pages(__GFP_COMP |
 					   (atomic ? GFP_ATOMIC : GFP_KERNEL),
 					   efx->rx_buffer_order);
 			if (unlikely(page == NULL))
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 42443f434569..0004c50d3c83 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -163,7 +163,7 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic)
 	do {
 		page = efx_reuse_page(rx_queue);
 		if (page == NULL) {
-			page = alloc_pages(__GFP_COLD | __GFP_COMP |
+			page = alloc_pages(__GFP_COMP |
 					   (atomic ? GFP_ATOMIC : GFP_KERNEL),
 					   efx->rx_buffer_order);
 			if (unlikely(page == NULL))
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
index e9672b1f9968..031cf9c3435a 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
@@ -335,7 +335,7 @@ static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata,
 	dma_addr_t pages_dma;
 
 	/* Try to obtain pages, decreasing order if necessary */
-	gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
+	gfp |= __GFP_COMP | __GFP_NOWARN;
 	while (order >= 0) {
 		pages = alloc_pages(gfp, order);
 		if (pages)
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 437d36289786..50d2b76771b5 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -906,7 +906,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 		sw_data[0] = (u32)bufptr;
 	} else {
 		/* Allocate a secondary receive queue entry */
-		page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD);
+		page = alloc_page(GFP_ATOMIC | GFP_DMA);
 		if (unlikely(!page)) {
 			dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n");
 			goto fail;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 511f8339fa96..5eec09d63fc0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -988,7 +988,6 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 	int err;
 	bool oom;
 
-	gfp |= __GFP_COLD;
 	do {
 		if (vi->mergeable_rx_bufs)
 			err = add_recvbuf_mergeable(vi, rq, gfp);
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index 9e538a59f09d..03e55bca4ada 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -1152,7 +1152,7 @@ static int mdc_read_page_remote(void *data, struct page *page0)
 	}
 
 	for (npages = 1; npages < max_pages; npages++) {
-		page = page_cache_alloc_cold(inode->i_mapping);
+		page = page_cache_alloc(inode->i_mapping);
 		if (!page)
 			break;
 		page_pool[npages] = page;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 23097cca2674..883bc7bb12c5 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -256,8 +256,7 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 			goto backing_page_already_present;
 
 		if (!newpage) {
-			newpage = __page_cache_alloc(cachefiles_gfp |
-						     __GFP_COLD);
+			newpage = __page_cache_alloc(cachefiles_gfp);
 			if (!newpage)
 				goto nomem_monitor;
 		}
@@ -493,8 +492,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 				goto backing_page_already_present;
 
 			if (!newpage) {
-				newpage = __page_cache_alloc(cachefiles_gfp |
-							     __GFP_COLD);
+				newpage = __page_cache_alloc(cachefiles_gfp);
 				if (!newpage)
 					goto nomem;
 			}
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f7e62d9096fe..1a4582b44d32 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -24,7 +24,6 @@ struct vm_area_struct;
 #define ___GFP_HIGH		0x20u
 #define ___GFP_IO		0x40u
 #define ___GFP_FS		0x80u
-#define ___GFP_COLD		0x100u
 #define ___GFP_NOWARN		0x200u
 #define ___GFP_RETRY_MAYFAIL	0x400u
 #define ___GFP_NOFAIL		0x800u
@@ -192,16 +191,12 @@ struct vm_area_struct;
 /*
  * Action modifiers
  *
- * __GFP_COLD indicates that the caller does not expect to be used in the near
- *   future. Where possible, a cache-cold page will be returned.
- *
  * __GFP_NOWARN suppresses allocation failure reports.
  *
  * __GFP_COMP address compound page metadata.
  *
  * __GFP_ZERO returns a zeroed page on success.
  */
-#define __GFP_COLD	((__force gfp_t)___GFP_COLD)
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 4c6790bb7afb..34ce3ebf97d5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -234,15 +234,9 @@ static inline struct page *page_cache_alloc(struct address_space *x)
 	return __page_cache_alloc(mapping_gfp_mask(x));
 }
 
-static inline struct page *page_cache_alloc_cold(struct address_space *x)
-{
-	return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
-}
-
 static inline gfp_t readahead_gfp_mask(struct address_space *x)
 {
-	return mapping_gfp_mask(x) |
-				  __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN;
+	return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN;
 }
 
 typedef int filler_t(void *, struct page *);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index aa1341474916..7c46fd0b8b64 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2672,7 +2672,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
 	 * 4.  __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to
 	 *     code in gfp_to_alloc_flags that should be enforcing this.
 	 */
-	gfp_mask |= __GFP_COLD | __GFP_COMP | __GFP_MEMALLOC;
+	gfp_mask |= __GFP_COMP | __GFP_MEMALLOC;
 
 	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
 }
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 79f6532f8a0b..50697a1d6621 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -467,9 +467,6 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  * Also it is possible to set different flags by OR'ing
  * in one or more of the following additional @flags:
  *
- * %__GFP_COLD - Request cache-cold pages instead of
- *   trying to return cache-warm pages.
- *
  * %__GFP_HIGH - This allocation has high priority and may use emergency pools.
  *
  * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 72162f3a03fa..dbe1bb058c09 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -32,7 +32,6 @@
 	{(unsigned long)__GFP_ATOMIC,		"__GFP_ATOMIC"},	\
 	{(unsigned long)__GFP_IO,		"__GFP_IO"},		\
 	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
-	{(unsigned long)__GFP_COLD,		"__GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
 	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
 	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index a917a301e201..bce0464524d8 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1884,7 +1884,7 @@ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
  */
 static inline int get_highmem_buffer(int safe_needed)
 {
-	buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed);
+	buffer = get_image_page(GFP_ATOMIC, safe_needed);
 	return buffer ? 0 : -ENOMEM;
 }
 
@@ -1945,7 +1945,7 @@ static int swsusp_alloc(struct memory_bitmap *copy_bm,
 		while (nr_pages-- > 0) {
 			struct page *page;
 
-			page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
+			page = alloc_image_page(GFP_ATOMIC);
 			if (!page)
 				goto err_out;
 			memory_bm_set_bit(copy_bm, page_to_pfn(page));
diff --git a/mm/filemap.c b/mm/filemap.c
index 90a9f261f85f..923fc2ebd74a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2272,7 +2272,7 @@ no_cached_page:
 		 * Ok, it wasn't cached, so we need to create a new
 		 * page..
 		 */
-		page = page_cache_alloc_cold(mapping);
+		page = page_cache_alloc(mapping);
 		if (!page) {
 			error = -ENOMEM;
 			goto out;
@@ -2384,7 +2384,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
 	int ret;
 
 	do {
-		page = __page_cache_alloc(gfp_mask|__GFP_COLD);
+		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			return -ENOMEM;
 
@@ -2788,7 +2788,7 @@ static struct page *do_read_cache_page(struct address_space *mapping,
 repeat:
 	page = find_get_page(mapping, index);
 	if (!page) {
-		page = __page_cache_alloc(gfp | __GFP_COLD);
+		page = __page_cache_alloc(gfp);
 		if (!page)
 			return ERR_PTR(-ENOMEM);
 		err = add_to_page_cache_lru(page, mapping, index, gfp);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f265d37b3152..370b64d03e3f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2336,7 +2336,7 @@ retry:
  */
 static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
-			int migratetype, bool cold)
+			int migratetype)
 {
 	int i, alloced = 0;
 
@@ -2358,10 +2358,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		 * merge IO requests if the physical pages are ordered
 		 * properly.
 		 */
-		if (likely(!cold))
-			list_add(&page->lru, list);
-		else
-			list_add_tail(&page->lru, list);
+		list_add(&page->lru, list);
 		list = &page->lru;
 		alloced++;
 		if (is_migrate_cma(get_pcppage_migratetype(page)))
@@ -2795,7 +2792,7 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 
 /* Remove page from the per-cpu list, caller must protect the list */
 static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
-			bool cold, struct per_cpu_pages *pcp,
+			struct per_cpu_pages *pcp,
 			struct list_head *list)
 {
 	struct page *page;
@@ -2804,16 +2801,12 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
 		if (list_empty(list)) {
 			pcp->count += rmqueue_bulk(zone, 0,
 					pcp->batch, list,
-					migratetype, cold);
+					migratetype);
 			if (unlikely(list_empty(list)))
 				return NULL;
 		}
 
-		if (cold)
-			page = list_last_entry(list, struct page, lru);
-		else
-			page = list_first_entry(list, struct page, lru);
-
+		page = list_first_entry(list, struct page, lru);
 		list_del(&page->lru);
 		pcp->count--;
 	} while (check_new_pcp(page));
@@ -2828,14 +2821,13 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 {
 	struct per_cpu_pages *pcp;
 	struct list_head *list;
-	bool cold = ((gfp_flags & __GFP_COLD) != 0);
 	struct page *page;
 	unsigned long flags;
 
 	local_irq_save(flags);
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
 	list = &pcp->lists[migratetype];
-	page = __rmqueue_pcplist(zone,  migratetype, cold, pcp, list);
+	page = __rmqueue_pcplist(zone,  migratetype, pcp, list);
 	if (page) {
 		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 		zone_statistics(preferred_zone, zone);
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 15dab691ea70..9158e5a81391 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -81,7 +81,7 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
 static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			    struct page **pages, int page_start, int page_end)
 {
-	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
+	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM;
 	unsigned int cpu, tcpu;
 	int i;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6cd057b41f34..9c68555bb906 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -353,7 +353,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
  */
 void *netdev_alloc_frag(unsigned int fragsz)
 {
-	return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+	return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(netdev_alloc_frag);
 
@@ -366,7 +366,7 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 
 void *napi_alloc_frag(unsigned int fragsz)
 {
-	return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+	return __napi_alloc_frag(fragsz, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(napi_alloc_frag);
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index cbf70738ef5f..ae11e4c3516a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -641,7 +641,6 @@ static const struct {
 	{ "__GFP_ATOMIC",		"_A" },
 	{ "__GFP_IO",			"I" },
 	{ "__GFP_FS",			"F" },
-	{ "__GFP_COLD",			"CO" },
 	{ "__GFP_NOWARN",		"NWR" },
 	{ "__GFP_RETRY_MAYFAIL",	"R" },
 	{ "__GFP_NOFAIL",		"NF" },
-- 
cgit v1.2.3


From 97f404ad3e53bf9ac598745066ba2f57c1da3039 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 15 Nov 2017 17:36:07 +0300
Subject: x86/selftests: Add test for mapping placement for 5-level paging

5-level paging provides a 56-bit virtual address space for user space
application. But the kernel defaults to mappings below the 47-bit address
space boundary, which is the upper bound for 4-level paging, unless an
application explicitely request it by using a mmap(2) address hint above
the 47-bit boundary. The kernel prevents mappings which spawn across the
47-bit boundary unless mmap(2) was invoked with MAP_FIXED.

Add a self-test that covers the corner cases of the interface and validates
the correctness of the implementation.

[ tglx: Massaged changelog once more ]

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20171115143607.81541-2-kirill.shutemov@linux.intel.com
---
 tools/testing/selftests/x86/5lvl.c   | 177 +++++++++++++++++++++++++++++++++++
 tools/testing/selftests/x86/Makefile |   2 +-
 2 files changed, 178 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/x86/5lvl.c

(limited to 'tools')

diff --git a/tools/testing/selftests/x86/5lvl.c b/tools/testing/selftests/x86/5lvl.c
new file mode 100644
index 000000000000..2eafdcd4c2b3
--- /dev/null
+++ b/tools/testing/selftests/x86/5lvl.c
@@ -0,0 +1,177 @@
+#include <stdio.h>
+#include <sys/mman.h>
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define PAGE_SIZE	4096
+#define LOW_ADDR	((void *) (1UL << 30))
+#define HIGH_ADDR	((void *) (1UL << 50))
+
+struct testcase {
+	void *addr;
+	unsigned long size;
+	unsigned long flags;
+	const char *msg;
+	unsigned int low_addr_required:1;
+	unsigned int keep_mapped:1;
+};
+
+static struct testcase testcases[] = {
+	{
+		.addr = NULL,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(NULL)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = LOW_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(LOW_ADDR)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR) again",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap(HIGH_ADDR, MAP_FIXED)",
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1) again",
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE),
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap((1UL << 47), 2 * PAGE_SIZE)",
+		.low_addr_required = 1,
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE / 2),
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap((1UL << 47), 2 * PAGE_SIZE / 2)",
+		.low_addr_required = 1,
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE),
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap((1UL << 47) - PAGE_SIZE, 2 * PAGE_SIZE, MAP_FIXED)",
+	},
+	{
+		.addr = NULL,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(NULL, MAP_HUGETLB)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = LOW_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(LOW_ADDR, MAP_HUGETLB)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR, MAP_HUGETLB)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR, MAP_HUGETLB) again",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap(HIGH_ADDR, MAP_FIXED | MAP_HUGETLB)",
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1, MAP_HUGETLB)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1, MAP_HUGETLB) again",
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE),
+		.size = 4UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap((1UL << 47), 4UL << 20, MAP_HUGETLB)",
+		.low_addr_required = 1,
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void *)((1UL << 47) - (2UL << 20)),
+		.size = 4UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap((1UL << 47) - (2UL << 20), 4UL << 20, MAP_FIXED | MAP_HUGETLB)",
+	},
+};
+
+int main(int argc, char **argv)
+{
+	int i;
+	void *p;
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		struct testcase *t = testcases + i;
+
+		p = mmap(t->addr, t->size, PROT_NONE, t->flags, -1, 0);
+
+		printf("%s: %p - ", t->msg, p);
+
+		if (p == MAP_FAILED) {
+			printf("FAILED\n");
+			continue;
+		}
+
+		if (t->low_addr_required && p >= (void *)(1UL << 47))
+			printf("FAILED\n");
+		else
+			printf("OK\n");
+		if (!t->keep_mapped)
+			munmap(p, t->size);
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 7b1adeee4b0f..939a337128db 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -11,7 +11,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
-- 
cgit v1.2.3


From a3f22d505f56bf3efd8eecd9b7adcc40a40a4a8e Mon Sep 17 00:00:00 2001
From: Pu Hou <bjhoupu@linux.vnet.ibm.com>
Date: Thu, 1 Sep 2016 10:48:22 +0200
Subject: s390/perf: add callback to perf to enable using AUX buffer

Perf tool need implement a callback to enable using AUX buffer. Perf
will do another mmap() to trigger the setup of AUX buffer in kernel
if there is such callback. The default size of the AUX buffer is set
properly according to the sampling frequency to avoid overflow. It
could also be manually set by -m option of perf.

The interface of perf is not changed. Diagnostic mode sampling
could be started by `perf record -e rBD000` like before.

Signed-off-by: Pu Hou <bjhoupu@linux.vnet.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 tools/perf/arch/s390/util/Build      |   2 +
 tools/perf/arch/s390/util/auxtrace.c | 118 +++++++++++++++++++++++++++++++++++
 2 files changed, 120 insertions(+)
 create mode 100644 tools/perf/arch/s390/util/auxtrace.c

(limited to 'tools')

diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 5bd7b9260cc0..397084382b23 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -4,3 +4,5 @@ libperf-y += kvm-stat.o
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
 libperf-y += machine.o
+
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
new file mode 100644
index 000000000000..6cb48e4cffd9
--- /dev/null
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -0,0 +1,118 @@
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../../util/evlist.h"
+#include "../../util/auxtrace.h"
+#include "../../util/evsel.h"
+
+#define PERF_EVENT_CPUM_SF		0xB0000 /* Event: Basic-sampling */
+#define PERF_EVENT_CPUM_SF_DIAG		0xBD000 /* Event: Combined-sampling */
+#define DEFAULT_AUX_PAGES		128
+#define DEFAULT_FREQ			4000
+
+static void cpumsf_free(struct auxtrace_record *itr)
+{
+	free(itr);
+}
+
+static size_t cpumsf_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+				    struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+
+static int
+cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused,
+		 struct perf_session *session __maybe_unused,
+		 struct auxtrace_info_event *auxtrace_info __maybe_unused,
+		 size_t priv_size __maybe_unused)
+{
+	return 0;
+}
+
+static unsigned long
+cpumsf_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return 0;
+}
+
+static int
+cpumsf_recording_options(struct auxtrace_record *ar __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 struct record_opts *opts)
+{
+	unsigned int factor = 1;
+	unsigned int pages;
+
+	opts->full_auxtrace = true;
+
+	/*
+	 * The AUX buffer size should be set properly to avoid
+	 * overflow of samples if it is not set explicitly.
+	 * DEFAULT_AUX_PAGES is an proper size when sampling frequency
+	 * is DEFAULT_FREQ. It is expected to hold about 1/2 second
+	 * of sampling data. The size used for AUX buffer will scale
+	 * according to the specified frequency and DEFAULT_FREQ.
+	 */
+	if (!opts->auxtrace_mmap_pages) {
+		if (opts->user_freq != UINT_MAX)
+			factor = (opts->user_freq + DEFAULT_FREQ
+				  - 1) / DEFAULT_FREQ;
+		pages = DEFAULT_AUX_PAGES * factor;
+		opts->auxtrace_mmap_pages = roundup_pow_of_two(pages);
+	}
+
+	return 0;
+}
+
+static int
+cpumsf_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+			      struct record_opts *opts __maybe_unused,
+			      const char *str __maybe_unused)
+{
+	return 0;
+}
+
+/*
+ * auxtrace_record__init is called when perf record
+ * check if the event really need auxtrace
+ */
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+					      int *err)
+{
+	struct auxtrace_record *aux;
+	struct perf_evsel *pos;
+	int diagnose = 0;
+
+	if (evlist->nr_entries == 0)
+		return NULL;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (pos->attr.config == PERF_EVENT_CPUM_SF_DIAG) {
+			diagnose = 1;
+			break;
+		}
+	}
+
+	if (!diagnose)
+		return NULL;
+
+	/* sampling in diagnose mode. alloc aux buffer */
+	aux = zalloc(sizeof(*aux));
+	if (aux == NULL) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	aux->parse_snapshot_options = cpumsf_parse_snapshot_options;
+	aux->recording_options = cpumsf_recording_options;
+	aux->info_priv_size = cpumsf_info_priv_size;
+	aux->info_fill = cpumsf_info_fill;
+	aux->free = cpumsf_free;
+	aux->reference = cpumsf_reference;
+
+	return aux;
+}
-- 
cgit v1.2.3


From f704ef44602fbf403e6722c7ed13f62d17e8cb20 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 19 Jan 2016 11:23:38 +0100
Subject: s390/perf: add support for perf_regs and libdw

With support for perf_regs and libdw, you can record and report
call graphs for user space programs. Simply invoke perf with
the --call-graph=dwarf command line option.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
[brueckner: added dwfl_thread_state_register_pc() call]
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 tools/perf/Makefile.config               |  6 ++-
 tools/perf/arch/s390/include/perf_regs.h | 63 ++++++++++++++++++++++++++++++++
 tools/perf/arch/s390/util/Build          |  1 +
 tools/perf/arch/s390/util/dwarf-regs.c   |  4 ++
 tools/perf/arch/s390/util/unwind-libdw.c | 40 ++++++++++++++++++++
 5 files changed, 113 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/arch/s390/include/perf_regs.h
 create mode 100644 tools/perf/arch/s390/util/unwind-libdw.c

(limited to 'tools')

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 63f534a0902f..ed65e82f034e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -53,6 +53,10 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(ARCH),s390)
+  NO_PERF_REGS := 0
+endif
+
 ifeq ($(NO_PERF_REGS),0)
   $(call detected,CONFIG_PERF_REGS)
 endif
@@ -61,7 +65,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc s390))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
new file mode 100644
index 000000000000..ac4b8c8c49e2
--- /dev/null
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -0,0 +1,63 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <../../../../arch/s390/include/uapi/asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK ((1ULL << PERF_REG_S390_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_S390_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
+
+#define PERF_REG_IP PERF_REG_S390_PC
+#define PERF_REG_SP PERF_REG_S390_R15
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_S390_R0:
+		return "R0";
+	case PERF_REG_S390_R1:
+		return "R1";
+	case PERF_REG_S390_R2:
+		return "R2";
+	case PERF_REG_S390_R3:
+		return "R3";
+	case PERF_REG_S390_R4:
+		return "R4";
+	case PERF_REG_S390_R5:
+		return "R5";
+	case PERF_REG_S390_R6:
+		return "R6";
+	case PERF_REG_S390_R7:
+		return "R7";
+	case PERF_REG_S390_R8:
+		return "R8";
+	case PERF_REG_S390_R9:
+		return "R9";
+	case PERF_REG_S390_R10:
+		return "R10";
+	case PERF_REG_S390_R11:
+		return "R11";
+	case PERF_REG_S390_R12:
+		return "R12";
+	case PERF_REG_S390_R13:
+		return "R13";
+	case PERF_REG_S390_R14:
+		return "R14";
+	case PERF_REG_S390_R15:
+		return "R15";
+	case PERF_REG_S390_MASK:
+		return "MASK";
+	case PERF_REG_S390_PC:
+		return "PC";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 397084382b23..4a233683c684 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-y += machine.o
 
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index 0dff5b2ed1e5..0cd7cba5d6ee 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -19,5 +19,9 @@ static const char *gpr_names[NUM_GPRS] = {
 
 const char *get_arch_regstr(unsigned int n)
 {
+	if (n == 64)
+		return "mask";
+	if (n == 65)
+		return "pc";
 	return (n >= NUM_GPRS) ? NULL : gpr_names[n];
 }
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
new file mode 100644
index 000000000000..281bbb82402a
--- /dev/null
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -0,0 +1,40 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_S390_MAX];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_S390_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(R0);
+	dwarf_regs[1]  = REG(R1);
+	dwarf_regs[2]  = REG(R2);
+	dwarf_regs[3]  = REG(R3);
+	dwarf_regs[4]  = REG(R4);
+	dwarf_regs[5]  = REG(R5);
+	dwarf_regs[6]  = REG(R6);
+	dwarf_regs[7]  = REG(R7);
+	dwarf_regs[8]  = REG(R8);
+	dwarf_regs[9]  = REG(R9);
+	dwarf_regs[10] = REG(R10);
+	dwarf_regs[11] = REG(R11);
+	dwarf_regs[12] = REG(R12);
+	dwarf_regs[13] = REG(R13);
+	dwarf_regs[14] = REG(R14);
+	dwarf_regs[15] = REG(R15);
+	dwarf_regs[16] = REG(MASK);
+	dwarf_regs[17] = REG(PC);
+
+	dwfl_thread_state_register_pc(thread, dwarf_regs[17]);
+	return dwfl_thread_state_registers(thread, 0, 16, dwarf_regs);
+}
-- 
cgit v1.2.3


From a9fc2db0a8abf51c81122799c5ae4808f2324b6d Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Wed, 8 Nov 2017 09:01:12 +0100
Subject: s390/perf: define common DWARF register string table

Instead of defining DWARF register to string table in dwarf-regs-table.h
and dwarf-regs.c, use a common table in dwarf-regs-table.h.

Ensure that the DWARF register table is up-to-date with
http://refspecs.linuxfoundation.org/ELF/zSeries/lzsabi0_s390/x1542.html.

For unwinding with libdw, also ensure to correctly setup the DWARF
register frame according to the register mappings.  Currently, libdw
supports up to 32 registers only.

Suggested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 tools/perf/arch/s390/include/dwarf-regs-table.h | 71 +++++++++++++++++++++++--
 tools/perf/arch/s390/util/dwarf-regs.c          | 15 ++----
 tools/perf/arch/s390/util/unwind-libdw.c        | 15 ++++--
 3 files changed, 80 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/arch/s390/include/dwarf-regs-table.h b/tools/perf/arch/s390/include/dwarf-regs-table.h
index 792d4c277225..671553525f41 100644
--- a/tools/perf/arch/s390/include/dwarf-regs-table.h
+++ b/tools/perf/arch/s390/include/dwarf-regs-table.h
@@ -1,9 +1,72 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifdef DEFINE_DWARF_REGSTR_TABLE
-/* This is included in perf/util/dwarf-regs.c */
+#ifndef S390_DWARF_REGS_TABLE_H
+#define S390_DWARF_REGS_TABLE_H
 
-static const char * const s390_regstr_tbl[] = {
+#define REG_DWARFNUM_NAME(reg, idx)	[idx] = "%" #reg
+
+/*
+ * For reference, see DWARF register mapping:
+ * http://refspecs.linuxfoundation.org/ELF/zSeries/lzsabi0_s390/x1542.html
+ */
+static const char * const s390_dwarf_regs[] = {
 	"%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
 	"%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+	REG_DWARFNUM_NAME(f0, 16),
+	REG_DWARFNUM_NAME(f1, 20),
+	REG_DWARFNUM_NAME(f2, 17),
+	REG_DWARFNUM_NAME(f3, 21),
+	REG_DWARFNUM_NAME(f4, 18),
+	REG_DWARFNUM_NAME(f5, 22),
+	REG_DWARFNUM_NAME(f6, 19),
+	REG_DWARFNUM_NAME(f7, 23),
+	REG_DWARFNUM_NAME(f8, 24),
+	REG_DWARFNUM_NAME(f9, 28),
+	REG_DWARFNUM_NAME(f10, 25),
+	REG_DWARFNUM_NAME(f11, 29),
+	REG_DWARFNUM_NAME(f12, 26),
+	REG_DWARFNUM_NAME(f13, 30),
+	REG_DWARFNUM_NAME(f14, 27),
+	REG_DWARFNUM_NAME(f15, 31),
+	REG_DWARFNUM_NAME(c0, 32),
+	REG_DWARFNUM_NAME(c1, 33),
+	REG_DWARFNUM_NAME(c2, 34),
+	REG_DWARFNUM_NAME(c3, 35),
+	REG_DWARFNUM_NAME(c4, 36),
+	REG_DWARFNUM_NAME(c5, 37),
+	REG_DWARFNUM_NAME(c6, 38),
+	REG_DWARFNUM_NAME(c7, 39),
+	REG_DWARFNUM_NAME(c8, 40),
+	REG_DWARFNUM_NAME(c9, 41),
+	REG_DWARFNUM_NAME(c10, 42),
+	REG_DWARFNUM_NAME(c11, 43),
+	REG_DWARFNUM_NAME(c12, 44),
+	REG_DWARFNUM_NAME(c13, 45),
+	REG_DWARFNUM_NAME(c14, 46),
+	REG_DWARFNUM_NAME(c15, 47),
+	REG_DWARFNUM_NAME(a0, 48),
+	REG_DWARFNUM_NAME(a1, 49),
+	REG_DWARFNUM_NAME(a2, 50),
+	REG_DWARFNUM_NAME(a3, 51),
+	REG_DWARFNUM_NAME(a4, 52),
+	REG_DWARFNUM_NAME(a5, 53),
+	REG_DWARFNUM_NAME(a6, 54),
+	REG_DWARFNUM_NAME(a7, 55),
+	REG_DWARFNUM_NAME(a8, 56),
+	REG_DWARFNUM_NAME(a9, 57),
+	REG_DWARFNUM_NAME(a10, 58),
+	REG_DWARFNUM_NAME(a11, 59),
+	REG_DWARFNUM_NAME(a12, 60),
+	REG_DWARFNUM_NAME(a13, 61),
+	REG_DWARFNUM_NAME(a14, 62),
+	REG_DWARFNUM_NAME(a15, 63),
+	REG_DWARFNUM_NAME(pswm, 64),
+	REG_DWARFNUM_NAME(pswa, 65),
 };
-#endif
+
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+#define s390_regstr_tbl s390_dwarf_regs
+
+#endif	/* DEFINE_DWARF_REGSTR_TABLE */
+#endif	/* S390_DWARF_REGS_TABLE_H */
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index 0cd7cba5d6ee..f47576ce13ea 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -9,19 +9,10 @@
 
 #include <stddef.h>
 #include <dwarf-regs.h>
-
-#define NUM_GPRS 16
-
-static const char *gpr_names[NUM_GPRS] = {
-	"%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
-	"%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
-};
+#include <linux/kernel.h>
+#include "dwarf-regs-table.h"
 
 const char *get_arch_regstr(unsigned int n)
 {
-	if (n == 64)
-		return "mask";
-	if (n == 65)
-		return "pc";
-	return (n >= NUM_GPRS) ? NULL : gpr_names[n];
+	return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
 }
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
index 281bbb82402a..ba8d98b8b09e 100644
--- a/tools/perf/arch/s390/util/unwind-libdw.c
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -1,21 +1,26 @@
+#include <linux/kernel.h>
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
 #include "../../util/event.h"
+#include "dwarf-regs-table.h"
 
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
 	struct unwind_info *ui = arg;
 	struct regs_dump *user_regs = &ui->sample->user_regs;
-	Dwarf_Word dwarf_regs[PERF_REG_S390_MAX];
+	Dwarf_Word dwarf_regs[ARRAY_SIZE(s390_dwarf_regs)];
 
 #define REG(r) ({						\
 	Dwarf_Word val = 0;					\
 	perf_reg_value(&val, user_regs, PERF_REG_S390_##r);	\
 	val;							\
 })
-
+	/*
+	 * For DWARF register mapping details,
+	 * see also perf/arch/s390/include/dwarf-regs-table.h
+	 */
 	dwarf_regs[0]  = REG(R0);
 	dwarf_regs[1]  = REG(R1);
 	dwarf_regs[2]  = REG(R2);
@@ -32,9 +37,9 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 	dwarf_regs[13] = REG(R13);
 	dwarf_regs[14] = REG(R14);
 	dwarf_regs[15] = REG(R15);
-	dwarf_regs[16] = REG(MASK);
-	dwarf_regs[17] = REG(PC);
+	dwarf_regs[64] = REG(MASK);
+	dwarf_regs[65] = REG(PC);
 
-	dwfl_thread_state_register_pc(thread, dwarf_regs[17]);
+	dwfl_thread_state_register_pc(thread, dwarf_regs[65]);
 	return dwfl_thread_state_registers(thread, 0, 16, dwarf_regs);
 }
-- 
cgit v1.2.3


From de9954b75e992d26a67d83990e6219dcb6edc3bf Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Wed, 8 Nov 2017 09:17:38 +0100
Subject: s390/perf: add perf register support for floating-point registers

For correct unwinding of user space processes, the floating-point
register contents are required.  For example, leaf functions might
use fp registers to temporarily store the return address.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 tools/perf/arch/s390/include/perf_regs.h | 32 ++++++++++++++++++++++++++++++++
 tools/perf/arch/s390/util/unwind-libdw.c | 20 +++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
index ac4b8c8c49e2..d2df54a6bc5a 100644
--- a/tools/perf/arch/s390/include/perf_regs.h
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -49,6 +49,38 @@ static inline const char *perf_reg_name(int id)
 		return "R14";
 	case PERF_REG_S390_R15:
 		return "R15";
+	case PERF_REG_S390_FP0:
+		return "FP0";
+	case PERF_REG_S390_FP1:
+		return "FP1";
+	case PERF_REG_S390_FP2:
+		return "FP2";
+	case PERF_REG_S390_FP3:
+		return "FP3";
+	case PERF_REG_S390_FP4:
+		return "FP4";
+	case PERF_REG_S390_FP5:
+		return "FP5";
+	case PERF_REG_S390_FP6:
+		return "FP6";
+	case PERF_REG_S390_FP7:
+		return "FP7";
+	case PERF_REG_S390_FP8:
+		return "FP8";
+	case PERF_REG_S390_FP9:
+		return "FP9";
+	case PERF_REG_S390_FP10:
+		return "FP10";
+	case PERF_REG_S390_FP11:
+		return "FP11";
+	case PERF_REG_S390_FP12:
+		return "FP12";
+	case PERF_REG_S390_FP13:
+		return "FP13";
+	case PERF_REG_S390_FP14:
+		return "FP14";
+	case PERF_REG_S390_FP15:
+		return "FP15";
 	case PERF_REG_S390_MASK:
 		return "MASK";
 	case PERF_REG_S390_PC:
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
index ba8d98b8b09e..387c698cdd1b 100644
--- a/tools/perf/arch/s390/util/unwind-libdw.c
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -37,9 +37,27 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 	dwarf_regs[13] = REG(R13);
 	dwarf_regs[14] = REG(R14);
 	dwarf_regs[15] = REG(R15);
+
+	dwarf_regs[16] = REG(FP0);
+	dwarf_regs[17] = REG(FP2);
+	dwarf_regs[18] = REG(FP4);
+	dwarf_regs[19] = REG(FP6);
+	dwarf_regs[20] = REG(FP1);
+	dwarf_regs[21] = REG(FP3);
+	dwarf_regs[22] = REG(FP5);
+	dwarf_regs[23] = REG(FP7);
+	dwarf_regs[24] = REG(FP8);
+	dwarf_regs[25] = REG(FP10);
+	dwarf_regs[26] = REG(FP12);
+	dwarf_regs[27] = REG(FP14);
+	dwarf_regs[28] = REG(FP9);
+	dwarf_regs[29] = REG(FP11);
+	dwarf_regs[30] = REG(FP13);
+	dwarf_regs[31] = REG(FP15);
+
 	dwarf_regs[64] = REG(MASK);
 	dwarf_regs[65] = REG(PC);
 
 	dwfl_thread_state_register_pc(thread, dwarf_regs[65]);
-	return dwfl_thread_state_registers(thread, 0, 16, dwarf_regs);
+	return dwfl_thread_state_registers(thread, 0, 32, dwarf_regs);
 }
-- 
cgit v1.2.3


From e4795e3bb7d7b3b3d066cea57fb459f869500284 Mon Sep 17 00:00:00 2001
From: Cheng Jian <cj.chengjian@huawei.com>
Date: Fri, 17 Nov 2017 15:28:23 -0800
Subject: tools/lib/traceevent/parse-filter.c: clean up clang build warning

The uniform structure filter_arg sets its union based on the difference
of enum filter_arg_type, However, some functions use implicit type
conversion obviously.

warning: implicit conversion from enumeration type 'enum filter_exp_type'
	 to different enumeration type 'enum filter_op_type'

warning: implicit conversion from enumeration type 'enum filter_cmp_type'
	 to different enumeration type 'enum filter_exp_type'

Link: http://lkml.kernel.org/r/1509938415-113825-1-git-send-email-cj.chengjian@huawei.com
Signed-off-by: Cheng Jian <cj.chengjian@huawei.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Xie XiuQi <xiexiuqi@huawei.com>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Steven Rostedt (Red Hat) <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/lib/traceevent/parse-filter.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 7c214ceb9386..315df0a70265 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -436,13 +436,13 @@ create_arg_exp(enum filter_exp_type etype)
 		return NULL;
 
 	arg->type = FILTER_ARG_EXP;
-	arg->op.type = etype;
+	arg->exp.type = etype;
 
 	return arg;
 }
 
 static struct filter_arg *
-create_arg_cmp(enum filter_exp_type etype)
+create_arg_cmp(enum filter_cmp_type ctype)
 {
 	struct filter_arg *arg;
 
@@ -452,7 +452,7 @@ create_arg_cmp(enum filter_exp_type etype)
 
 	/* Use NUM and change if necessary */
 	arg->type = FILTER_ARG_NUM;
-	arg->op.type = etype;
+	arg->num.type = ctype;
 
 	return arg;
 }
-- 
cgit v1.2.3


From 64c349f4ae78723248c474531d0cbc524fc5ba77 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 17 Nov 2017 15:31:22 -0800
Subject: mm: add infrastructure for get_user_pages_fast() benchmarking

Performance of get_user_pages_fast() is critical for some workloads, but
it's tricky to test it directly.

This patch provides /sys/kernel/debug/gup_benchmark that helps with
testing performance of it.

See tools/testing/selftests/vm/gup_benchmark.c for userspace
counterpart.

Link: http://lkml.kernel.org/r/20170908215603.9189-2-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thorsten Leemhuis <regressions@leemhuis.info>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/Kconfig                                 |   9 +++
 mm/Makefile                                |   1 +
 mm/gup_benchmark.c                         | 100 +++++++++++++++++++++++++++++
 tools/testing/selftests/vm/Makefile        |   1 +
 tools/testing/selftests/vm/gup_benchmark.c |  91 ++++++++++++++++++++++++++
 5 files changed, 202 insertions(+)
 create mode 100644 mm/gup_benchmark.c
 create mode 100644 tools/testing/selftests/vm/gup_benchmark.c

(limited to 'tools')

diff --git a/mm/Kconfig b/mm/Kconfig
index 9c4bdddd80c2..03ff7703d322 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -756,3 +756,12 @@ config PERCPU_STATS
 	  This feature collects and exposes statistics via debugfs. The
 	  information includes global and per chunk statistics, which can
 	  be used to help understand percpu memory usage.
+
+config GUP_BENCHMARK
+	bool "Enable infrastructure for get_user_pages_fast() benchmarking"
+	default n
+	help
+	  Provides /sys/kernel/debug/gup_benchmark that helps with testing
+	  performance of get_user_pages_fast().
+
+	  See tools/testing/selftests/vm/gup_benchmark.c
diff --git a/mm/Makefile b/mm/Makefile
index e7ebd176fb93..e669f02c5a54 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -80,6 +80,7 @@ obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
 obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
 obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
+obj-$(CONFIG_GUP_BENCHMARK) += gup_benchmark.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
new file mode 100644
index 000000000000..5c8e2abeaa15
--- /dev/null
+++ b/mm/gup_benchmark.c
@@ -0,0 +1,100 @@
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+
+#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+	__u64 delta_usec;
+	__u64 addr;
+	__u64 size;
+	__u32 nr_pages_per_call;
+	__u32 flags;
+};
+
+static int __gup_benchmark_ioctl(unsigned int cmd,
+		struct gup_benchmark *gup)
+{
+	ktime_t start_time, end_time;
+	unsigned long i, nr, nr_pages, addr, next;
+	struct page **pages;
+
+	nr_pages = gup->size / PAGE_SIZE;
+	pages = kvmalloc(sizeof(void *) * nr_pages, GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	i = 0;
+	nr = gup->nr_pages_per_call;
+	start_time = ktime_get();
+	for (addr = gup->addr; addr < gup->addr + gup->size; addr = next) {
+		if (nr != gup->nr_pages_per_call)
+			break;
+
+		next = addr + nr * PAGE_SIZE;
+		if (next > gup->addr + gup->size) {
+			next = gup->addr + gup->size;
+			nr = (next - addr) / PAGE_SIZE;
+		}
+
+		nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i);
+		i += nr;
+	}
+	end_time = ktime_get();
+
+	gup->delta_usec = ktime_us_delta(end_time, start_time);
+	gup->size = addr - gup->addr;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (!pages[i])
+			break;
+		put_page(pages[i]);
+	}
+
+	kvfree(pages);
+	return 0;
+}
+
+static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
+		unsigned long arg)
+{
+	struct gup_benchmark gup;
+	int ret;
+
+	if (cmd != GUP_FAST_BENCHMARK)
+		return -EINVAL;
+
+	if (copy_from_user(&gup, (void __user *)arg, sizeof(gup)))
+		return -EFAULT;
+
+	ret = __gup_benchmark_ioctl(cmd, &gup);
+	if (ret)
+		return ret;
+
+	if (copy_to_user((void __user *)arg, &gup, sizeof(gup)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static const struct file_operations gup_benchmark_fops = {
+	.open = nonseekable_open,
+	.unlocked_ioctl = gup_benchmark_ioctl,
+};
+
+static int gup_benchmark_init(void)
+{
+	void *ret;
+
+	ret = debugfs_create_file_unsafe("gup_benchmark", 0600, NULL, NULL,
+			&gup_benchmark_fops);
+	if (!ret)
+		pr_warn("Failed to create gup_benchmark in debugfs");
+
+	return 0;
+}
+
+late_initcall(gup_benchmark_init);
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index e49eca1915f8..7f45806bd863 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -18,6 +18,7 @@ TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += virtual_address_range
+TEST_GEN_FILES += gup_benchmark
 
 TEST_PROGS := run_vmtests
 
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
new file mode 100644
index 000000000000..36df55132036
--- /dev/null
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -0,0 +1,91 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+#define MB (1UL << 20)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+	__u64 delta_usec;
+	__u64 addr;
+	__u64 size;
+	__u32 nr_pages_per_call;
+	__u32 flags;
+};
+
+int main(int argc, char **argv)
+{
+	struct gup_benchmark gup;
+	unsigned long size = 128 * MB;
+	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	char *p;
+
+	while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+		switch (opt) {
+		case 'm':
+			size = atoi(optarg) * MB;
+			break;
+		case 'r':
+			repeats = atoi(optarg);
+			break;
+		case 'n':
+			nr_pages = atoi(optarg);
+			break;
+		case 't':
+			thp = 1;
+			break;
+		case 'T':
+			thp = 0;
+			break;
+		case 'w':
+			write = 1;
+		default:
+			return -1;
+		}
+	}
+
+	gup.nr_pages_per_call = nr_pages;
+	gup.flags = write;
+
+	fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
+	if (fd == -1)
+		perror("open"), exit(1);
+
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (p == MAP_FAILED)
+		perror("mmap"), exit(1);
+	gup.addr = (unsigned long)p;
+
+	if (thp == 1)
+		madvise(p, size, MADV_HUGEPAGE);
+	else if (thp == 0)
+		madvise(p, size, MADV_NOHUGEPAGE);
+
+	for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
+		p[0] = 0;
+
+	for (i = 0; i < repeats; i++) {
+		gup.size = size;
+		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+			perror("ioctl"), exit(1);
+
+		printf("Time: %lld us", gup.delta_usec);
+		if (gup.size != size)
+			printf(", truncated (size: %lld)", gup.size);
+		printf("\n");
+	}
+
+	return 0;
+}
-- 
cgit v1.2.3


From 16f8259ca77d04f95e5ca90be1b1894ed45816c0 Mon Sep 17 00:00:00 2001
From: Bjørn Forsman <bjorn.forsman@gmail.com>
Date: Sun, 5 Nov 2017 10:44:16 +0100
Subject: kbuild: /bin/pwd -> pwd
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most places use pwd and rely on $PATH lookup. Moving the remaining
absolute path /bin/pwd users over for consistency.

Also, a reason for doing /bin/pwd -> pwd instead of the other way around
is because I believe build systems should make little assumptions on
host filesystem layout. Case in point, we do this kind of patching
already in NixOS.

Ref. commit 028568d84da3cfca49f5f846eeeef01441d70451
("kbuild: revert $(realpath ...) to $(shell cd ... && /bin/pwd)").

Signed-off-by: Bjørn Forsman <bjorn.forsman@gmail.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/ia64/xen.txt     | 2 +-
 Makefile                       | 2 +-
 tools/power/cpupower/Makefile  | 2 +-
 tools/scripts/Makefile.include | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/Documentation/ia64/xen.txt b/Documentation/ia64/xen.txt
index c61a99f7c8bb..a12c74ce2773 100644
--- a/Documentation/ia64/xen.txt
+++ b/Documentation/ia64/xen.txt
@@ -41,7 +41,7 @@ Getting and Building Xen and Dom0
 
  5. make initrd for Dom0/DomU
     # make -C linux-2.6.18-xen.hg ARCH=ia64 modules_install \
-      O=$(/bin/pwd)/build-linux-2.6.18-xen_ia64
+      O=$(pwd)/build-linux-2.6.18-xen_ia64
     # mkinitrd -f /boot/efi/efi/redhat/initrd-2.6.18.8-xen.img \
       2.6.18.8-xen --builtin mptspi --builtin mptbase \
       --builtin mptscsih --builtin uhci-hcd --builtin ohci-hcd \
diff --git a/Makefile b/Makefile
index efb942ad0b55..533fc1d0f283 100644
--- a/Makefile
+++ b/Makefile
@@ -132,7 +132,7 @@ ifneq ($(KBUILD_OUTPUT),)
 # check that the output directory actually exists
 saved-output := $(KBUILD_OUTPUT)
 KBUILD_OUTPUT := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) \
-								&& /bin/pwd)
+								&& pwd)
 $(if $(KBUILD_OUTPUT),, \
      $(error failed to create output directory "$(saved-output)"))
 
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index da205d1fa03c..1dd5f4fcffd5 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 := $(shell cd $(OUTPUT) && /bin/pwd)
+OUTDIR := $(shell cd $(OUTPUT) && pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 654efd9768fd..3fab179b1aba 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -13,7 +13,7 @@ endif
 
 # check that the output directory actually exists
 ifneq ($(OUTPUT),)
-OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+OUTDIR := $(shell cd $(OUTPUT) && pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
-- 
cgit v1.2.3


From 1f6f4cb7ba219b00a3fa9afe8049fa16444d8b52 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 20 Nov 2017 15:21:53 -0800
Subject: bpf: offload: rename the ifindex field

bpf_target_prog seems long and clunky, rename it to prog_ifindex.
We don't want to call this field just ifindex, because maps
may need a similar field in the future and bpf_attr members for
programs and maps are unnamed.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h       | 2 +-
 kernel/bpf/offload.c           | 2 +-
 kernel/bpf/syscall.c           | 4 ++--
 tools/include/uapi/linux/bpf.h | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e880ae6434ee..3f626df42516 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -262,7 +262,7 @@ union bpf_attr {
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
-		__u32		prog_target_ifindex;	/* ifindex of netdev to prep for */
+		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ac187f9ee182..a778e5df7e26 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -29,7 +29,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 	init_waitqueue_head(&offload->verifier_done);
 
 	rtnl_lock();
-	offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex);
+	offload->netdev = __dev_get_by_index(net, attr->prog_ifindex);
 	if (!offload->netdev) {
 		rtnl_unlock();
 		kfree(offload);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 09badc37e864..8e9d065bb7cd 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1118,7 +1118,7 @@ struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
 EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex
+#define	BPF_PROG_LOAD_LAST_FIELD prog_ifindex
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -1181,7 +1181,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	atomic_set(&prog->aux->refcnt, 1);
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
-	if (attr->prog_target_ifindex) {
+	if (attr->prog_ifindex) {
 		err = bpf_prog_offload_init(prog, attr);
 		if (err)
 			goto free_prog;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e880ae6434ee..3f626df42516 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -262,7 +262,7 @@ union bpf_attr {
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
-		__u32		prog_target_ifindex;	/* ifindex of netdev to prep for */
+		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
-- 
cgit v1.2.3


From 51aa423959b0ab62169c98b90566a0628ba096b8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 20 Nov 2017 15:21:58 -0800
Subject: bpftool: revert printing program device bound info

This reverts commit 928631e05495 ("bpftool: print program device bound
info").  We will remove this API and redo it right in -next.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/prog.c       | 31 -------------------------------
 tools/include/uapi/linux/bpf.h |  6 ------
 2 files changed, 37 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index f45c44ef9bec..ad619b96c276 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -41,7 +41,6 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
-#include <net/if.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
@@ -230,21 +229,6 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 		     info->tag[0], info->tag[1], info->tag[2], info->tag[3],
 		     info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
 
-	if (info->status & BPF_PROG_STATUS_DEV_BOUND) {
-		jsonw_name(json_wtr, "dev");
-		if (info->ifindex) {
-			char name[IF_NAMESIZE];
-
-			if (!if_indextoname(info->ifindex, name))
-				jsonw_printf(json_wtr, "\"ifindex:%d\"",
-					     info->ifindex);
-			else
-				jsonw_printf(json_wtr, "\"%s\"", name);
-		} else {
-			jsonw_printf(json_wtr, "\"unknown\"");
-		}
-	}
-
 	if (info->load_time) {
 		char buf[32];
 
@@ -302,21 +286,6 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 
 	printf("tag ");
 	fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
-	printf(" ");
-
-	if (info->status & BPF_PROG_STATUS_DEV_BOUND) {
-		printf("dev ");
-		if (info->ifindex) {
-			char name[IF_NAMESIZE];
-
-			if (!if_indextoname(info->ifindex, name))
-				printf("ifindex:%d ", info->ifindex);
-			else
-				printf("%s ", name);
-		} else {
-			printf("unknown ");
-		}
-	}
 	printf("\n");
 
 	if (info->load_time) {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3f626df42516..4c223ab30293 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -897,10 +897,6 @@ enum sk_action {
 
 #define BPF_TAG_SIZE	8
 
-enum bpf_prog_status {
-	BPF_PROG_STATUS_DEV_BOUND	= (1 << 0),
-};
-
 struct bpf_prog_info {
 	__u32 type;
 	__u32 id;
@@ -914,8 +910,6 @@ struct bpf_prog_info {
 	__u32 nr_map_ids;
 	__aligned_u64 map_ids;
 	char name[BPF_OBJ_NAME_LEN];
-	__u32 ifindex;
-	__u32 status;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
-- 
cgit v1.2.3


From a6400120d042397675fcf694060779d21e9e762d Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 10 Nov 2017 16:12:29 -0800
Subject: x86/mpx/selftests: Fix up weird arrays

The MPX hardware data structurse are defined in a weird way: they define
their size in bytes and then union that with the type with which we want
to access them.

Yes, this is weird, but it does work.  But, new GCC's complain that we
are accessing the array out of bounds.  Just make it a zero-sized array
so gcc will stop complaining.  There was not really a bug here.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171111001229.58A7933D@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/testing/selftests/x86/mpx-hw.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/x86/mpx-hw.h b/tools/testing/selftests/x86/mpx-hw.h
index 3f0093911f03..d1b61ab870f8 100644
--- a/tools/testing/selftests/x86/mpx-hw.h
+++ b/tools/testing/selftests/x86/mpx-hw.h
@@ -52,14 +52,14 @@
 struct mpx_bd_entry {
 	union {
 		char x[MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES];
-		void *contents[1];
+		void *contents[0];
 	};
 } __attribute__((packed));
 
 struct mpx_bt_entry {
 	union {
 		char x[MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES];
-		unsigned long contents[1];
+		unsigned long contents[0];
 	};
 } __attribute__((packed));
 
-- 
cgit v1.2.3


From 91c49c2deb96ffc3c461eaae70219d89224076b7 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 10 Nov 2017 16:12:31 -0800
Subject: x86/pkeys/selftests: Rename 'si_pkey' to 'siginfo_pkey'

'si_pkey' is now #defined to be the name of the new siginfo field that
protection keys uses.  Rename it not to conflict.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171111001231.DFFC8285@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/testing/selftests/x86/protection_keys.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 7a1cc0e56d2d..bc1b0735bb50 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -250,7 +250,7 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	unsigned long ip;
 	char *fpregs;
 	u32 *pkru_ptr;
-	u64 si_pkey;
+	u64 siginfo_pkey;
 	u32 *si_pkey_ptr;
 	int pkru_offset;
 	fpregset_t fpregset;
@@ -292,9 +292,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
 	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
 	dump_mem(si_pkey_ptr - 8, 24);
-	si_pkey = *si_pkey_ptr;
-	pkey_assert(si_pkey < NR_PKEYS);
-	last_si_pkey = si_pkey;
+	siginfo_pkey = *si_pkey_ptr;
+	pkey_assert(siginfo_pkey < NR_PKEYS);
+	last_si_pkey = siginfo_pkey;
 
 	if ((si->si_code == SEGV_MAPERR) ||
 	    (si->si_code == SEGV_ACCERR) ||
@@ -306,7 +306,7 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
 	/* need __rdpkru() version so we do not do shadow_pkru checking */
 	dprintf1("signal pkru from  pkru: %08x\n", __rdpkru());
-	dprintf1("si_pkey from siginfo: %jx\n", si_pkey);
+	dprintf1("pkey from siginfo: %jx\n", siginfo_pkey);
 	*(u64 *)pkru_ptr = 0x00000000;
 	dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
 	pkru_faults++;
-- 
cgit v1.2.3


From 7b659ee3e1fe0e8eb39730afb903c64e25490ec4 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 10 Nov 2017 16:12:32 -0800
Subject: x86/pkeys/selftests: Fix protection keys write() warning

write() is marked as having a must-check return value.  Check it and
abort if we fail to write an error message from a signal handler.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171111001232.94813E58@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/testing/selftests/x86/pkey-helpers.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
index 3818f25391c2..b3cb7670e026 100644
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ b/tools/testing/selftests/x86/pkey-helpers.h
@@ -30,6 +30,7 @@ static inline void sigsafe_printf(const char *format, ...)
 	if (!dprint_in_signal) {
 		vprintf(format, ap);
 	} else {
+		int ret;
 		int len = vsnprintf(dprint_in_signal_buffer,
 				    DPRINT_IN_SIGNAL_BUF_SIZE,
 				    format, ap);
@@ -39,7 +40,9 @@ static inline void sigsafe_printf(const char *format, ...)
 		 */
 		if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
 			len = DPRINT_IN_SIGNAL_BUF_SIZE;
-		write(1, dprint_in_signal_buffer, len);
+		ret = write(1, dprint_in_signal_buffer, len);
+		if (ret < 0)
+			abort();
 	}
 	va_end(ap);
 }
-- 
cgit v1.2.3


From f1a8b8e3d98b0b3d1d88d119f52cc85d05ab3189 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 21 Nov 2017 11:23:40 -0800
Subject: bpf: change bpf_probe_write_user to bpf_trace_printk in test_verifier

There are four tests in test_verifier using bpf_probe_write_user
helper. These four tests will emit the following kernel messages
  [   12.974753] test_verifier[220] is installing a program with bpf_probe_write_user
                                    helper that may corrupt user memory!
  [   12.979285] test_verifier[220] is installing a program with bpf_probe_write_user
                                    helper that may corrupt user memory!
  ......

This may confuse certain users. This patch replaces bpf_probe_write_user
with bpf_trace_printk. The test_verifier already uses bpf_trace_printk
earlier in the test and a trace_printk warning message has been printed.
So this patch does not emit any more kernel messages.

Fixes: b6ff63911232 ("bpf: fix and add test cases for ARG_CONST_SIZE_OR_ZERO semantics change")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 39 ++++++++++++-----------------
 1 file changed, 16 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index bf092b83e453..2a5267bef160 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4377,11 +4377,10 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-			BPF_MOV64_IMM(BPF_REG_1, 0),
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
@@ -4481,14 +4480,12 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
 				offsetof(struct test_val, foo)),
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-			BPF_MOV64_IMM(BPF_REG_1, 0),
-			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
@@ -4618,18 +4615,16 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-			BPF_MOV64_IMM(BPF_REG_1, 0),
-			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
-		.errstr = "R2 min value is outside of the array range",
+		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -4760,20 +4755,18 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
 			BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
-				offsetof(struct test_val, foo), 4),
+				offsetof(struct test_val, foo), 3),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-			BPF_MOV64_IMM(BPF_REG_1, 0),
-			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
-		.errstr = "R2 min value is outside of the array range",
+		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
-- 
cgit v1.2.3


From db1ac4964fa172803a0fea83033cd35d380a8a77 Mon Sep 17 00:00:00 2001
From: Gianluca Borello <g.borello@gmail.com>
Date: Wed, 22 Nov 2017 18:32:53 +0000
Subject: bpf: introduce ARG_PTR_TO_MEM_OR_NULL

With the current ARG_PTR_TO_MEM/ARG_PTR_TO_UNINIT_MEM semantics, an helper
argument can be NULL when the next argument type is ARG_CONST_SIZE_OR_ZERO
and the verifier can prove the value of this next argument is 0. However,
most helpers are just interested in handling <!NULL, 0>, so forcing them to
deal with <NULL, 0> makes the implementation of those helpers more
complicated for no apparent benefits, requiring them to explicitly handle
those corner cases with checks that bpf programs could start relying upon,
preventing the possibility of removing them later.

Solve this by making ARG_PTR_TO_MEM/ARG_PTR_TO_UNINIT_MEM never accept NULL
even when ARG_CONST_SIZE_OR_ZERO is set, and introduce a new argument type
ARG_PTR_TO_MEM_OR_NULL to explicitly deal with the NULL case.

Currently, the only helper that needs this is bpf_csum_diff_proto(), so
change arg1 and arg3 to this new type as well.

Also add a new battery of tests that explicitly test the
!ARG_PTR_TO_MEM_OR_NULL combination: all the current ones testing the
various <NULL, 0> variations are focused on bpf_csum_diff, so cover also
other helpers.

Signed-off-by: Gianluca Borello <g.borello@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h                         |   1 +
 kernel/bpf/verifier.c                       |   4 +-
 net/core/filter.c                           |   4 +-
 tools/testing/selftests/bpf/test_verifier.c | 113 ++++++++++++++++++++++++++--
 4 files changed, 112 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 76c577281d78..e55e4255a210 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -78,6 +78,7 @@ enum bpf_arg_type {
 	 * functions that access data on eBPF program stack
 	 */
 	ARG_PTR_TO_MEM,		/* pointer to valid memory (stack, packet, map value) */
+	ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */
 	ARG_PTR_TO_UNINIT_MEM,	/* pointer to memory does not need to be initialized,
 				 * helper function must fill all bytes or clear
 				 * them in error case.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dd54d20ace2f..308b0638ec5d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1384,13 +1384,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		if (type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_PTR_TO_MEM ||
+		   arg_type == ARG_PTR_TO_MEM_OR_NULL ||
 		   arg_type == ARG_PTR_TO_UNINIT_MEM) {
 		expected_type = PTR_TO_STACK;
 		/* One exception here. In case function allows for NULL to be
 		 * passed in as argument, it's a SCALAR_VALUE type. Final test
 		 * happens during stack boundary checking.
 		 */
-		if (register_is_null(*reg))
+		if (register_is_null(*reg) &&
+		    arg_type == ARG_PTR_TO_MEM_OR_NULL)
 			/* final test in check_stack_boundary() */;
 		else if (!type_is_pkt_pointer(type) &&
 			 type != PTR_TO_MAP_VALUE &&
diff --git a/net/core/filter.c b/net/core/filter.c
index 1afa17935954..6a85e67fafce 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1646,9 +1646,9 @@ static const struct bpf_func_proto bpf_csum_diff_proto = {
 	.gpl_only	= false,
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
-	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_PTR_TO_MEM_OR_NULL,
 	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg5_type	= ARG_ANYTHING,
 };
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 2a5267bef160..3c64f30cf63c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -5631,7 +5631,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
 	{
-		"helper access to variable memory: size = 0 allowed on NULL",
+		"helper access to variable memory: size = 0 allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_2, 0),
@@ -5645,7 +5645,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size > 0 not allowed on NULL",
+		"helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_2, 0),
@@ -5663,7 +5663,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size = 0 allowed on != NULL stack pointer",
+		"helper access to variable memory: size = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
@@ -5680,7 +5680,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size = 0 allowed on != NULL map pointer",
+		"helper access to variable memory: size = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5702,7 +5702,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer",
+		"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5727,7 +5727,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size possible = 0 allowed on != NULL map pointer",
+		"helper access to variable memory: size possible = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5750,7 +5750,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size possible = 0 allowed on != NULL packet pointer",
+		"helper access to variable memory: size possible = 0 allowed on != NULL packet pointer (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
 				    offsetof(struct __sk_buff, data)),
@@ -5771,6 +5771,105 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
+	{
+		"helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 type=inv expected=fp",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
+	{
+		"helper access to variable memory: size > 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 type=inv expected=fp",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
+	{
+		"helper access to variable memory: size = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
+	{
+		"helper access to variable memory: size = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 2),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
 	{
 		"helper access to variable memory: 8 bytes leak",
 		.insns = {
-- 
cgit v1.2.3


From 297d6b6e56c2977fc504c61bbeeaa21296923f89 Mon Sep 17 00:00:00 2001
From: Paul Meyer <Paul.Meyer@microsoft.com>
Date: Tue, 14 Nov 2017 13:06:47 -0700
Subject: hv: kvp: Avoid reading past allocated blocks from KVP file

While reading in more than one block (50) of KVP records, the allocation
goes per block, but the reads used the total number of allocated records
(without resetting the pointer/stream). This causes the records buffer to
overrun when the refresh reads more than one block over the previous
capacity (e.g. reading more than 100 KVP records whereas the in-memory
database was empty before).

Fix this by reading the correct number of KVP records from file each time.

Signed-off-by: Paul Meyer <Paul.Meyer@microsoft.com>
Signed-off-by: Long Li <longli@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/hv/hv_kvp_daemon.c | 70 ++++++++++--------------------------------------
 1 file changed, 14 insertions(+), 56 deletions(-)

(limited to 'tools')

diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index eaa3bec273c8..4c99c57736ce 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -193,11 +193,14 @@ static void kvp_update_mem_state(int pool)
 	for (;;) {
 		readp = &record[records_read];
 		records_read += fread(readp, sizeof(struct kvp_record),
-					ENTRIES_PER_BLOCK * num_blocks,
-					filep);
+				ENTRIES_PER_BLOCK * num_blocks - records_read,
+				filep);
 
 		if (ferror(filep)) {
-			syslog(LOG_ERR, "Failed to read file, pool: %d", pool);
+			syslog(LOG_ERR,
+				"Failed to read file, pool: %d; error: %d %s",
+				 pool, errno, strerror(errno));
+			kvp_release_lock(pool);
 			exit(EXIT_FAILURE);
 		}
 
@@ -210,6 +213,7 @@ static void kvp_update_mem_state(int pool)
 
 			if (record == NULL) {
 				syslog(LOG_ERR, "malloc failed");
+				kvp_release_lock(pool);
 				exit(EXIT_FAILURE);
 			}
 			continue;
@@ -224,15 +228,11 @@ static void kvp_update_mem_state(int pool)
 	fclose(filep);
 	kvp_release_lock(pool);
 }
+
 static int kvp_file_init(void)
 {
 	int  fd;
-	FILE *filep;
-	size_t records_read;
 	char *fname;
-	struct kvp_record *record;
-	struct kvp_record *readp;
-	int num_blocks;
 	int i;
 	int alloc_unit = sizeof(struct kvp_record) * ENTRIES_PER_BLOCK;
 
@@ -246,61 +246,19 @@ static int kvp_file_init(void)
 
 	for (i = 0; i < KVP_POOL_COUNT; i++) {
 		fname = kvp_file_info[i].fname;
-		records_read = 0;
-		num_blocks = 1;
 		sprintf(fname, "%s/.kvp_pool_%d", KVP_CONFIG_LOC, i);
 		fd = open(fname, O_RDWR | O_CREAT | O_CLOEXEC, 0644 /* rw-r--r-- */);
 
 		if (fd == -1)
 			return 1;
 
-
-		filep = fopen(fname, "re");
-		if (!filep) {
-			close(fd);
-			return 1;
-		}
-
-		record = malloc(alloc_unit * num_blocks);
-		if (record == NULL) {
-			fclose(filep);
-			close(fd);
-			return 1;
-		}
-		for (;;) {
-			readp = &record[records_read];
-			records_read += fread(readp, sizeof(struct kvp_record),
-					ENTRIES_PER_BLOCK,
-					filep);
-
-			if (ferror(filep)) {
-				syslog(LOG_ERR, "Failed to read file, pool: %d",
-				       i);
-				exit(EXIT_FAILURE);
-			}
-
-			if (!feof(filep)) {
-				/*
-				 * We have more data to read.
-				 */
-				num_blocks++;
-				record = realloc(record, alloc_unit *
-						num_blocks);
-				if (record == NULL) {
-					fclose(filep);
-					close(fd);
-					return 1;
-				}
-				continue;
-			}
-			break;
-		}
 		kvp_file_info[i].fd = fd;
-		kvp_file_info[i].num_blocks = num_blocks;
-		kvp_file_info[i].records = record;
-		kvp_file_info[i].num_records = records_read;
-		fclose(filep);
-
+		kvp_file_info[i].num_blocks = 1;
+		kvp_file_info[i].records = malloc(alloc_unit);
+		if (kvp_file_info[i].records == NULL)
+			return 1;
+		kvp_file_info[i].num_records = 0;
+		kvp_update_mem_state(i);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 9b85c2d4508563f4bb1de0d971ed02fea0d0d757 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 28 Nov 2017 17:44:28 -0800
Subject: tools: bpftool: fix crash on bad parameters with JSON

If bad or unrecognised parameters are specified after JSON output is
requested, `usage()` will try to output null JSON object before the
writer is created.

To prevent this, create the writer as soon as the `--json` option is
parsed.

Fixes: 004b45c0e51a ("tools: bpftool: provide JSON output for all possible commands")
Reported-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d6e4762170a4..14ad54a1c404 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -291,7 +291,15 @@ int main(int argc, char **argv)
 			pretty_output = true;
 			/* fall through */
 		case 'j':
-			json_output = true;
+			if (!json_output) {
+				json_wtr = jsonw_new(stdout);
+				if (!json_wtr) {
+					p_err("failed to create JSON writer");
+					return -1;
+				}
+				json_output = true;
+			}
+			jsonw_pretty(json_wtr, pretty_output);
 			break;
 		case 'f':
 			show_pinned = true;
@@ -306,15 +314,6 @@ int main(int argc, char **argv)
 	if (argc < 0)
 		usage();
 
-	if (json_output) {
-		json_wtr = jsonw_new(stdout);
-		if (!json_wtr) {
-			p_err("failed to create JSON writer");
-			return -1;
-		}
-		jsonw_pretty(json_wtr, pretty_output);
-	}
-
 	bfd_init();
 
 	ret = cmd_select(cmds, argc, argv, do_help);
-- 
cgit v1.2.3


From 7868620a3c15dbc661fb5d849de403ac04624c50 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 28 Nov 2017 17:44:29 -0800
Subject: tools: bpftool: clean up the JSON writer before exiting in usage()

The writer is cleaned at the end of the main function, but not if the
program exits sooner in usage(). Let's keep it clean and destroy the
writer before exiting.

Destruction and actual call to exit() are moved to another function so
that clean exit can also be performed without printing usage() hints.

Fixes: d35efba99d92 ("tools: bpftool: introduce --json and --pretty options")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.c | 10 +++++++++-
 tools/bpf/bpftool/main.h |  3 ++-
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 14ad54a1c404..d72dd73a4016 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -58,11 +58,19 @@ bool show_pinned;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
 
+static void __noreturn clean_and_exit(int i)
+{
+	if (json_output)
+		jsonw_destroy(&json_wtr);
+
+	exit(i);
+}
+
 void usage(void)
 {
 	last_do_help(last_argc - 1, last_argv + 1);
 
-	exit(-1);
+	clean_and_exit(-1);
 }
 
 static int do_help(int argc, char **argv)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 9c191e222d6f..0b60ddfb2b93 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -41,6 +41,7 @@
 #include <stdbool.h>
 #include <stdio.h>
 #include <linux/bpf.h>
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/hashtable.h>
 
@@ -80,7 +81,7 @@ void p_info(const char *fmt, ...);
 
 bool is_prefix(const char *pfx, const char *str);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
-void usage(void) __attribute__((noreturn));
+void usage(void) __noreturn;
 
 struct pinned_obj_table {
 	DECLARE_HASHTABLE(table, 16);
-- 
cgit v1.2.3


From 146882a37da7aa566c7ec088b42c6495d769f2ba Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 28 Nov 2017 17:44:30 -0800
Subject: tools: bpftool: make error message from getopt_long() JSON-friendly

If `getopt_long()` meets an unknown option, it prints its own error
message to standard error output. While this does not strictly break
JSON output, it is the only case bpftool prints something to standard
error output if JSON output is required. All other errors are printed on
standard output as JSON objects, so that an external program does not
have to parse stderr.

This is changed by setting the global variable `opterr` to 0.
Furthermore, p_err() is used to reproduce the error message in a more
JSON-friendly way, so that users still get to know what the erroneous
option is.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d72dd73a4016..d294bc8168be 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -288,6 +288,7 @@ int main(int argc, char **argv)
 	hash_init(prog_table.table);
 	hash_init(map_table.table);
 
+	opterr = 0;
 	while ((opt = getopt_long(argc, argv, "Vhpjf",
 				  options, NULL)) >= 0) {
 		switch (opt) {
@@ -313,7 +314,11 @@ int main(int argc, char **argv)
 			show_pinned = true;
 			break;
 		default:
-			usage();
+			p_err("unrecognized option '%s'", argv[optind - 1]);
+			if (json_output)
+				clean_and_exit(-1);
+			else
+				usage();
 		}
 	}
 
-- 
cgit v1.2.3


From 0d954eeb99eee63964a07a68fcac61e1df8488e7 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 28 Nov 2017 17:44:31 -0800
Subject: tools: bpftool: remove spurious line break from error message

The end-of-line character inside the string would break JSON compliance.
Remove it, `p_err()` already adds a '\n' character for plain output
anyway.

Fixes: 9a5ab8bf1d6d ("tools: bpftool: turn err() and info() macros into functions")
Reported-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 0b60ddfb2b93..bff330b49791 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -51,7 +51,7 @@
 
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
-#define BAD_ARG()	({ p_err("what is '%s'?\n", *argv); -1; })
+#define BAD_ARG()	({ p_err("what is '%s'?", *argv); -1; })
 
 #define ERR_MAX_LEN	1024
 
-- 
cgit v1.2.3


From 507e590da398a0e3438d563b5e736c3f2a7749d7 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 28 Nov 2017 17:44:32 -0800
Subject: tools: bpftool: unify installation directories

Programs and documentation not managed by package manager are generally
installed under /usr/local/, instead of the user's home directory. In
particular, `man` is generally able to find manual pages under
`/usr/local/share/man`.

bpftool generally follows perf's example, and perf installs to home
directory. However bpftool requires root credentials, so it seems
sensible to follow the more common convention of installing files under
/usr/local instead. So, make /usr/local the default prefix for
installing the binary with `make install`, and the documentation with
`make doc-install`. Also, create /usr/local/sbin if it does not exist.

Note that the bash-completion file, however, is still installed under
/usr/share/bash-completion/completions, as the default setup for bash
does not attempt to load completion files under /usr/local/.

Reported-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/Makefile | 2 +-
 tools/bpf/bpftool/Makefile               | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index bde77d7c4390..37292bb5ce60 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -6,7 +6,7 @@ RM ?= rm -f
 
 # Make the path relative to DESTDIR, not prefix
 ifndef DESTDIR
-prefix?=$(HOME)
+prefix ?= /usr/local
 endif
 mandir ?= $(prefix)/share/man
 man8dir = $(mandir)/man8
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 813826c50936..c5b21f2cbca5 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -45,8 +45,8 @@ $(LIBBPF)-clean:
 	$(call QUIET_CLEAN, libbpf)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null
 
-prefix = /usr
-bash_compdir ?= $(prefix)/share/bash-completion/completions
+prefix = /usr/local
+bash_compdir ?= /usr/share/bash-completion/completions
 
 CC = gcc
 
@@ -76,6 +76,7 @@ clean: $(LIBBPF)-clean
 	$(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
 
 install:
+	install -m 0755 -d $(prefix)/sbin
 	install $(OUTPUT)bpftool $(prefix)/sbin/bpftool
 	install -m 0755 -d $(bash_compdir)
 	install -m 0644 bash-completion/bpftool $(bash_compdir)
-- 
cgit v1.2.3


From ad3cda064402b69148faf5f7cd1ac8c2eee52645 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 28 Nov 2017 17:44:33 -0800
Subject: tools: bpftool: declare phony targets as such

In the Makefile, targets install, doc and doc-install should be added to
.PHONY. Let's fix this.

Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index c5b21f2cbca5..ec3052c0b004 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -89,5 +89,5 @@ doc-install:
 
 FORCE:
 
-.PHONY: all clean FORCE
+.PHONY: all clean FORCE install doc doc-install
 .DEFAULT_GOAL := all
-- 
cgit v1.2.3


From 1ac7c8a78be85f84b019d3d2742d1a9f07255cc5 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Wed, 29 Nov 2017 15:24:22 -0700
Subject: usbip: fix usbip attach to find a port that matches the requested
 speed

usbip attach fails to find a free port when the device on the first port
is a USB_SPEED_SUPER device and non-super speed device is being attached.
It keeps checking the first port and returns without a match getting stuck
in a loop.

Fix it check to find the first port with matching speed.

Reported-by: Juan Zea <juan.zea@qindel.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/usb/usbip/libsrc/vhci_driver.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
index 5727dfb15a83..8a1cd1616de4 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.c
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -329,9 +329,17 @@ err:
 int usbip_vhci_get_free_port(uint32_t speed)
 {
 	for (int i = 0; i < vhci_driver->nports; i++) {
-		if (speed == USB_SPEED_SUPER &&
-		    vhci_driver->idev[i].hub != HUB_SPEED_SUPER)
-			continue;
+
+		switch (speed) {
+		case	USB_SPEED_SUPER:
+			if (vhci_driver->idev[i].hub != HUB_SPEED_SUPER)
+				continue;
+		break;
+		default:
+			if (vhci_driver->idev[i].hub != HUB_SPEED_HIGH)
+				continue;
+		break;
+		}
 
 		if (vhci_driver->idev[i].status == VDEV_ST_NULL)
 			return vhci_driver->idev[i].port;
-- 
cgit v1.2.3


From 2b279419567105d63f1e524bb1ac34ae8f918e5d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 30 Nov 2017 08:52:42 -0800
Subject: tools/bpf: adjust rlimit RLIMIT_MEMLOCK for test_verifier_log

The default rlimit RLIMIT_MEMLOCK is 64KB. In certain cases,
e.g. in a test machine mimicking our production system, this test may
fail due to unable to charge the required memory for prog load:
  # ./test_verifier_log
  Test log_level 0...
  ERROR: Program load returned: ret:-1/errno:1, expected ret:-1/errno:22

Changing the default rlimit RLIMIT_MEMLOCK to unlimited makes
the test always pass.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier_log.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c
index 3cc0b561489e..e9626cf5607a 100644
--- a/tools/testing/selftests/bpf/test_verifier_log.c
+++ b/tools/testing/selftests/bpf/test_verifier_log.c
@@ -3,6 +3,8 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 
 #include <linux/bpf.h>
 #include <linux/filter.h>
@@ -131,11 +133,16 @@ static void test_log_bad(char *log, size_t log_len, int log_level)
 
 int main(int argc, char **argv)
 {
+	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
 	char full_log[LOG_SIZE];
 	char log[LOG_SIZE];
 	size_t want_len;
 	int i;
 
+	/* allow unlimited locked memory to have more consistent error code */
+	if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0)
+		perror("Unable to lift memlock rlimit");
+
 	memset(log, 1, LOG_SIZE);
 
 	/* Test incorrect attr */
-- 
cgit v1.2.3