From 42765ede5c54ca915de5bfeab83be97207e46f68 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 1 Nov 2019 15:28:06 -0700
Subject: selftests/bpf: Remove too strict field offset relo test cases

As libbpf is going to gain support for more field relocations, including field
size, some restrictions about exact size match are going to be lifted. Remove
test cases that explicitly test such failures.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191101222810.1246166-2-andriin@fb.com
---
 .../btf__core_reloc_arrays___err_wrong_val_type.c  |  3 +
 .../btf__core_reloc_arrays___err_wrong_val_type1.c |  3 -
 .../btf__core_reloc_arrays___err_wrong_val_type2.c |  3 -
 .../progs/btf__core_reloc_ints___err_bitfield.c    |  3 -
 .../progs/btf__core_reloc_ints___err_wrong_sz_16.c |  3 -
 .../progs/btf__core_reloc_ints___err_wrong_sz_32.c |  3 -
 .../progs/btf__core_reloc_ints___err_wrong_sz_64.c |  3 -
 .../progs/btf__core_reloc_ints___err_wrong_sz_8.c  |  3 -
 .../testing/selftests/bpf/progs/core_reloc_types.h | 70 +---------------------
 9 files changed, 4 insertions(+), 90 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c

diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c
new file mode 100644
index 000000000000..f5a7c832d0f2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_wrong_val_type x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c
deleted file mode 100644
index 795a5b729176..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_arrays___err_wrong_val_type1 x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c
deleted file mode 100644
index 3af74b837c4d..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_arrays___err_wrong_val_type2 x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c
deleted file mode 100644
index 50369e8320a0..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_ints___err_bitfield x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c
deleted file mode 100644
index 823bac13d641..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_ints___err_wrong_sz_16 x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c
deleted file mode 100644
index b44f3be18535..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_ints___err_wrong_sz_32 x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c
deleted file mode 100644
index 9a3dd2099c0f..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_ints___err_wrong_sz_64 x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c
deleted file mode 100644
index 9f11ef5f6e88..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_ints___err_wrong_sz_8 x) {}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index f5939d9d5c61..3fe54f6f82cf 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -386,14 +386,7 @@ struct core_reloc_arrays___err_non_array {
 	struct core_reloc_arrays_substruct d[1][2];
 };
 
-struct core_reloc_arrays___err_wrong_val_type1 {
-	char a[5]; /* char instead of int */
-	char b[2][3][4];
-	struct core_reloc_arrays_substruct c[3];
-	struct core_reloc_arrays_substruct d[1][2];
-};
-
-struct core_reloc_arrays___err_wrong_val_type2 {
+struct core_reloc_arrays___err_wrong_val_type {
 	int a[5];
 	char b[2][3][4];
 	int c[3]; /* value is not a struct */
@@ -589,67 +582,6 @@ struct core_reloc_ints___bool {
 	int64_t		s64_field;
 };
 
-struct core_reloc_ints___err_bitfield {
-	uint8_t		u8_field;
-	int8_t		s8_field;
-	uint16_t	u16_field;
-	int16_t		s16_field;
-	uint32_t	u32_field: 32; /* bitfields are not supported */
-	int32_t		s32_field;
-	uint64_t	u64_field;
-	int64_t		s64_field;
-};
-
-struct core_reloc_ints___err_wrong_sz_8 {
-	uint16_t	u8_field; /* not 8-bit anymore */
-	int16_t		s8_field; /* not 8-bit anymore */
-
-	uint16_t	u16_field;
-	int16_t		s16_field;
-	uint32_t	u32_field;
-	int32_t		s32_field;
-	uint64_t	u64_field;
-	int64_t		s64_field;
-};
-
-struct core_reloc_ints___err_wrong_sz_16 {
-	uint8_t		u8_field;
-	int8_t		s8_field;
-
-	uint32_t	u16_field; /* not 16-bit anymore */
-	int32_t		s16_field; /* not 16-bit anymore */
-
-	uint32_t	u32_field;
-	int32_t		s32_field;
-	uint64_t	u64_field;
-	int64_t		s64_field;
-};
-
-struct core_reloc_ints___err_wrong_sz_32 {
-	uint8_t		u8_field;
-	int8_t		s8_field;
-	uint16_t	u16_field;
-	int16_t		s16_field;
-
-	uint64_t	u32_field; /* not 32-bit anymore */
-	int64_t		s32_field; /* not 32-bit anymore */
-
-	uint64_t	u64_field;
-	int64_t		s64_field;
-};
-
-struct core_reloc_ints___err_wrong_sz_64 {
-	uint8_t		u8_field;
-	int8_t		s8_field;
-	uint16_t	u16_field;
-	int16_t		s16_field;
-	uint32_t	u32_field;
-	int32_t		s32_field;
-
-	uint32_t	u64_field; /* not 64-bit anymore */
-	int32_t		s64_field; /* not 64-bit anymore */
-};
-
 /*
  * MISC
  */
-- 
cgit v1.2.3


From ee26dade0e3bcd8a34ae7520e373fb69365fce7a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 1 Nov 2019 15:28:07 -0700
Subject: libbpf: Add support for relocatable bitfields

Add support for the new field relocation kinds, necessary to support
relocatable bitfield reads. Provide macro for abstracting necessary code doing
full relocatable bitfield extraction into u64 value. Two separate macros are
provided:
- BPF_CORE_READ_BITFIELD macro for direct memory read-enabled BPF programs
(e.g., typed raw tracepoints). It uses direct memory dereference to extract
bitfield backing integer value.
- BPF_CORE_READ_BITFIELD_PROBED macro for cases where bpf_probe_read() needs
to be used to extract same backing integer value.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191101222810.1246166-3-andriin@fb.com
---
 tools/lib/bpf/bpf_core_read.h   |  72 ++++++++++++++
 tools/lib/bpf/libbpf.c          | 211 ++++++++++++++++++++++++++++------------
 tools/lib/bpf/libbpf_internal.h |   4 +
 3 files changed, 227 insertions(+), 60 deletions(-)

diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index a273df3784f4..0935cd68e7de 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -12,9 +12,81 @@
  */
 enum bpf_field_info_kind {
 	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
+	BPF_FIELD_BYTE_SIZE = 1,
 	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
+	BPF_FIELD_SIGNED = 3,
+	BPF_FIELD_LSHIFT_U64 = 4,
+	BPF_FIELD_RSHIFT_U64 = 5,
 };
 
+#define __CORE_RELO(src, field, info)					      \
+	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read((void *)dst,					      \
+		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
+		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#else
+/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so
+ * for big-endian we need to adjust destination pointer accordingly, based on
+ * field byte size
+ */
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)),  \
+		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
+		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#endif
+
+/*
+ * Extract bitfield, identified by src->field, and put its value into u64
+ * *res. All this is done in relocatable manner, so bitfield changes such as
+ * signedness, bit size, offset changes, this will be handled automatically.
+ * This version of macro is using bpf_probe_read() to read underlying integer
+ * storage. Macro functions as an expression and its return type is
+ * bpf_probe_read()'s return value: 0, on success, <0 on error.
+ */
+#define BPF_CORE_READ_BITFIELD_PROBED(src, field, res) ({		      \
+	unsigned long long val;						      \
+									      \
+	*res = 0;							      \
+	val = __CORE_BITFIELD_PROBE_READ(res, src, field);		      \
+	if (!val) {							      \
+		*res <<= __CORE_RELO(src, field, LSHIFT_U64);		      \
+		val = __CORE_RELO(src, field, RSHIFT_U64);		      \
+		if (__CORE_RELO(src, field, SIGNED))			      \
+			*res = ((long long)*res) >> val;		      \
+		else							      \
+			*res = ((unsigned long long)*res) >> val;	      \
+		val = 0;						      \
+	}								      \
+	val;								      \
+})
+
+/*
+ * Extract bitfield, identified by src->field, and return its value as u64.
+ * This version of macro is using direct memory reads and should be used from
+ * BPF program types that support such functionality (e.g., typed raw
+ * tracepoints).
+ */
+#define BPF_CORE_READ_BITFIELD(s, field) ({				      \
+	const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \
+	unsigned long long val;						      \
+									      \
+	switch (__CORE_RELO(s, field, BYTE_SIZE)) {			      \
+	case 1: val = *(const unsigned char *)p;			      \
+	case 2: val = *(const unsigned short *)p;			      \
+	case 4: val = *(const unsigned int *)p;				      \
+	case 8: val = *(const unsigned long long *)p;			      \
+	}								      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
 /*
  * Convenience macro to check that field actually exists in target kernel's.
  * Returns:
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7aa2a2a22cef..482af749f9cf 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2470,8 +2470,8 @@ struct bpf_core_spec {
 	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
 	/* raw spec length */
 	int raw_len;
-	/* field byte offset represented by spec */
-	__u32 offset;
+	/* field bit offset represented by spec */
+	__u32 bit_offset;
 };
 
 static bool str_is_empty(const char *s)
@@ -2482,8 +2482,8 @@ static bool str_is_empty(const char *s)
 /*
  * Turn bpf_field_reloc into a low- and high-level spec representation,
  * validating correctness along the way, as well as calculating resulting
- * field offset (in bytes), specified by accessor string. Low-level spec
- * captures every single level of nestedness, including traversing anonymous
+ * field bit offset, specified by accessor string. Low-level spec captures
+ * every single level of nestedness, including traversing anonymous
  * struct/union members. High-level one only captures semantically meaningful
  * "turning points": named fields and array indicies.
  * E.g., for this case:
@@ -2555,7 +2555,7 @@ static int bpf_core_spec_parse(const struct btf *btf,
 	sz = btf__resolve_size(btf, id);
 	if (sz < 0)
 		return sz;
-	spec->offset = access_idx * sz;
+	spec->bit_offset = access_idx * sz * 8;
 
 	for (i = 1; i < spec->raw_len; i++) {
 		t = skip_mods_and_typedefs(btf, id, &id);
@@ -2566,17 +2566,13 @@ static int bpf_core_spec_parse(const struct btf *btf,
 
 		if (btf_is_composite(t)) {
 			const struct btf_member *m;
-			__u32 offset;
+			__u32 bit_offset;
 
 			if (access_idx >= btf_vlen(t))
 				return -EINVAL;
-			if (btf_member_bitfield_size(t, access_idx))
-				return -EINVAL;
 
-			offset = btf_member_bit_offset(t, access_idx);
-			if (offset % 8)
-				return -EINVAL;
-			spec->offset += offset / 8;
+			bit_offset = btf_member_bit_offset(t, access_idx);
+			spec->bit_offset += bit_offset;
 
 			m = btf_members(t) + access_idx;
 			if (m->name_off) {
@@ -2605,7 +2601,7 @@ static int bpf_core_spec_parse(const struct btf *btf,
 			sz = btf__resolve_size(btf, id);
 			if (sz < 0)
 				return sz;
-			spec->offset += access_idx * sz;
+			spec->bit_offset += access_idx * sz * 8;
 		} else {
 			pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n",
 				type_id, spec_str, i, id, btf_kind(t));
@@ -2706,12 +2702,12 @@ err_out:
 }
 
 /* Check two types for compatibility, skipping const/volatile/restrict and
- * typedefs, to ensure we are relocating offset to the compatible entities:
+ * typedefs, to ensure we are relocating compatible entities:
  *   - any two STRUCTs/UNIONs are compatible and can be mixed;
  *   - any two FWDs are compatible;
  *   - any two PTRs are always compatible;
  *   - for ENUMs, check sizes, names are ignored;
- *   - for INT, size and bitness should match, signedness is ignored;
+ *   - for INT, size and signedness are ignored;
  *   - for ARRAY, dimensionality is ignored, element types are checked for
  *     compatibility recursively;
  *   - everything else shouldn't be ever a target of relocation.
@@ -2743,10 +2739,11 @@ recur:
 	case BTF_KIND_ENUM:
 		return local_type->size == targ_type->size;
 	case BTF_KIND_INT:
+		/* just reject deprecated bitfield-like integers; all other
+		 * integers are by default compatible between each other
+		 */
 		return btf_int_offset(local_type) == 0 &&
-		       btf_int_offset(targ_type) == 0 &&
-		       local_type->size == targ_type->size &&
-		       btf_int_bits(local_type) == btf_int_bits(targ_type);
+		       btf_int_offset(targ_type) == 0;
 	case BTF_KIND_ARRAY:
 		local_id = btf_array(local_type)->type;
 		targ_id = btf_array(targ_type)->type;
@@ -2762,7 +2759,7 @@ recur:
  * Given single high-level named field accessor in local type, find
  * corresponding high-level accessor for a target type. Along the way,
  * maintain low-level spec for target as well. Also keep updating target
- * offset.
+ * bit offset.
  *
  * Searching is performed through recursive exhaustive enumeration of all
  * fields of a struct/union. If there are any anonymous (embedded)
@@ -2801,21 +2798,16 @@ static int bpf_core_match_member(const struct btf *local_btf,
 	n = btf_vlen(targ_type);
 	m = btf_members(targ_type);
 	for (i = 0; i < n; i++, m++) {
-		__u32 offset;
+		__u32 bit_offset;
 
-		/* bitfield relocations not supported */
-		if (btf_member_bitfield_size(targ_type, i))
-			continue;
-		offset = btf_member_bit_offset(targ_type, i);
-		if (offset % 8)
-			continue;
+		bit_offset = btf_member_bit_offset(targ_type, i);
 
 		/* too deep struct/union/array nesting */
 		if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
 			return -E2BIG;
 
 		/* speculate this member will be the good one */
-		spec->offset += offset / 8;
+		spec->bit_offset += bit_offset;
 		spec->raw_spec[spec->raw_len++] = i;
 
 		targ_name = btf__name_by_offset(targ_btf, m->name_off);
@@ -2844,7 +2836,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
 			return found;
 		}
 		/* member turned out not to be what we looked for */
-		spec->offset -= offset / 8;
+		spec->bit_offset -= bit_offset;
 		spec->raw_len--;
 	}
 
@@ -2853,7 +2845,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
 
 /*
  * Try to match local spec to a target type and, if successful, produce full
- * target spec (high-level, low-level + offset).
+ * target spec (high-level, low-level + bit offset).
  */
 static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 			       const struct btf *targ_btf, __u32 targ_id,
@@ -2916,13 +2908,110 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 			sz = btf__resolve_size(targ_btf, targ_id);
 			if (sz < 0)
 				return sz;
-			targ_spec->offset += local_acc->idx * sz;
+			targ_spec->bit_offset += local_acc->idx * sz * 8;
 		}
 	}
 
 	return 1;
 }
 
+static int bpf_core_calc_field_relo(const struct bpf_program *prog,
+				    const struct bpf_field_reloc *relo,
+				    const struct bpf_core_spec *spec,
+				    __u32 *val, bool *validate)
+{
+	const struct bpf_core_accessor *acc = &spec->spec[spec->len - 1];
+	const struct btf_type *t = btf__type_by_id(spec->btf, acc->type_id);
+	__u32 byte_off, byte_sz, bit_off, bit_sz;
+	const struct btf_member *m;
+	const struct btf_type *mt;
+	bool bitfield;
+
+	/* a[n] accessor needs special handling */
+	if (!acc->name) {
+		if (relo->kind != BPF_FIELD_BYTE_OFFSET) {
+			pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access'\n",
+				bpf_program__title(prog, false),
+				relo->kind, relo->insn_off / 8);
+			return -EINVAL;
+		}
+		*val = spec->bit_offset / 8;
+		if (validate)
+			*validate = true;
+		return 0;
+	}
+
+	m = btf_members(t) + acc->idx;
+	mt = skip_mods_and_typedefs(spec->btf, m->type, NULL);
+	bit_off = spec->bit_offset;
+	bit_sz = btf_member_bitfield_size(t, acc->idx);
+
+	bitfield = bit_sz > 0;
+	if (bitfield) {
+		byte_sz = mt->size;
+		byte_off = bit_off / 8 / byte_sz * byte_sz;
+		/* figure out smallest int size necessary for bitfield load */
+		while (bit_off + bit_sz - byte_off * 8 > byte_sz * 8) {
+			if (byte_sz >= 8) {
+				/* bitfield can't be read with 64-bit read */
+				pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n",
+					bpf_program__title(prog, false),
+					relo->kind, relo->insn_off / 8);
+				return -E2BIG;
+			}
+			byte_sz *= 2;
+			byte_off = bit_off / 8 / byte_sz * byte_sz;
+		}
+	} else {
+		byte_sz = mt->size;
+		byte_off = spec->bit_offset / 8;
+		bit_sz = byte_sz * 8;
+	}
+
+	/* for bitfields, all the relocatable aspects are ambiguous and we
+	 * might disagree with compiler, so turn off validation of expected
+	 * value, except for signedness
+	 */
+	if (validate)
+		*validate = !bitfield;
+
+	switch (relo->kind) {
+	case BPF_FIELD_BYTE_OFFSET:
+		*val = byte_off;
+		break;
+	case BPF_FIELD_BYTE_SIZE:
+		*val = byte_sz;
+		break;
+	case BPF_FIELD_SIGNED:
+		/* enums will be assumed unsigned */
+		*val = btf_is_enum(mt) ||
+		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
+		if (validate)
+			*validate = true; /* signedness is never ambiguous */
+		break;
+	case BPF_FIELD_LSHIFT_U64:
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+		*val = 64 - (bit_off + bit_sz - byte_off  * 8);
+#else
+		*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
+#endif
+		break;
+	case BPF_FIELD_RSHIFT_U64:
+		*val = 64 - bit_sz;
+		if (validate)
+			*validate = true; /* right shift is never ambiguous */
+		break;
+	case BPF_FIELD_EXISTS:
+	default:
+		pr_warn("prog '%s': unknown relo %d at insn #%d\n",
+			bpf_program__title(prog, false),
+			relo->kind, relo->insn_off / 8);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * Patch relocatable BPF instruction.
  *
@@ -2942,36 +3031,31 @@ static int bpf_core_reloc_insn(struct bpf_program *prog,
 			       const struct bpf_core_spec *local_spec,
 			       const struct bpf_core_spec *targ_spec)
 {
+	bool failed = false, validate = true;
 	__u32 orig_val, new_val;
 	struct bpf_insn *insn;
-	int insn_idx;
+	int insn_idx, err;
 	__u8 class;
 
 	if (relo->insn_off % sizeof(struct bpf_insn))
 		return -EINVAL;
 	insn_idx = relo->insn_off / sizeof(struct bpf_insn);
 
-	switch (relo->kind) {
-	case BPF_FIELD_BYTE_OFFSET:
-		orig_val = local_spec->offset;
-		if (targ_spec) {
-			new_val = targ_spec->offset;
-		} else {
-			pr_warn("prog '%s': patching insn #%d w/ failed reloc, imm %d -> %d\n",
-				bpf_program__title(prog, false), insn_idx,
-				orig_val, -1);
-			new_val = (__u32)-1;
-		}
-		break;
-	case BPF_FIELD_EXISTS:
+	if (relo->kind == BPF_FIELD_EXISTS) {
 		orig_val = 1; /* can't generate EXISTS relo w/o local field */
 		new_val = targ_spec ? 1 : 0;
-		break;
-	default:
-		pr_warn("prog '%s': unknown relo %d at insn #%d'\n",
-			bpf_program__title(prog, false),
-			relo->kind, insn_idx);
-		return -EINVAL;
+	} else if (!targ_spec) {
+		failed = true;
+		new_val = (__u32)-1;
+	} else {
+		err = bpf_core_calc_field_relo(prog, relo, local_spec,
+					       &orig_val, &validate);
+		if (err)
+			return err;
+		err = bpf_core_calc_field_relo(prog, relo, targ_spec,
+					       &new_val, NULL);
+		if (err)
+			return err;
 	}
 
 	insn = &prog->insns[insn_idx];
@@ -2980,12 +3064,17 @@ static int bpf_core_reloc_insn(struct bpf_program *prog,
 	if (class == BPF_ALU || class == BPF_ALU64) {
 		if (BPF_SRC(insn->code) != BPF_K)
 			return -EINVAL;
-		if (insn->imm != orig_val)
+		if (!failed && validate && insn->imm != orig_val) {
+			pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n",
+				bpf_program__title(prog, false), insn_idx,
+				insn->imm, orig_val, new_val);
 			return -EINVAL;
+		}
+		orig_val = insn->imm;
 		insn->imm = new_val;
-		pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n",
-			 bpf_program__title(prog, false),
-			 insn_idx, orig_val, new_val);
+		pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n",
+			 bpf_program__title(prog, false), insn_idx,
+			 failed ? " w/ failed reloc" : "", orig_val, new_val);
 	} else {
 		pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n",
 			bpf_program__title(prog, false),
@@ -3103,7 +3192,8 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
 		libbpf_print(level, "%d%s", spec->raw_spec[i],
 			     i == spec->raw_len - 1 ? " => " : ":");
 
-	libbpf_print(level, "%u @ &x", spec->offset);
+	libbpf_print(level, "%u.%u @ &x",
+		     spec->bit_offset / 8, spec->bit_offset % 8);
 
 	for (i = 0; i < spec->len; i++) {
 		if (spec->spec[i].name)
@@ -3217,7 +3307,8 @@ static int bpf_core_reloc_field(struct bpf_program *prog,
 		return -EINVAL;
 	}
 
-	pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx);
+	pr_debug("prog '%s': relo #%d: kind %d, spec is ", prog_name, relo_idx,
+		 relo->kind);
 	bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
 	libbpf_print(LIBBPF_DEBUG, "\n");
 
@@ -3257,13 +3348,13 @@ static int bpf_core_reloc_field(struct bpf_program *prog,
 
 		if (j == 0) {
 			targ_spec = cand_spec;
-		} else if (cand_spec.offset != targ_spec.offset) {
+		} else if (cand_spec.bit_offset != targ_spec.bit_offset) {
 			/* if there are many candidates, they should all
-			 * resolve to the same offset
+			 * resolve to the same bit offset
 			 */
 			pr_warn("prog '%s': relo #%d: offset ambiguity: %u != %u\n",
-				prog_name, relo_idx, cand_spec.offset,
-				targ_spec.offset);
+				prog_name, relo_idx, cand_spec.bit_offset,
+				targ_spec.bit_offset);
 			return -EINVAL;
 		}
 
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index bd6f48ea407b..97ac17a64a58 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -158,7 +158,11 @@ struct bpf_line_info_min {
  */
 enum bpf_field_info_kind {
 	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
+	BPF_FIELD_BYTE_SIZE = 1,
 	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
+	BPF_FIELD_SIGNED = 3,
+	BPF_FIELD_LSHIFT_U64 = 4,
+	BPF_FIELD_RSHIFT_U64 = 5,
 };
 
 /* The minimum bpf_field_reloc checked by the loader
-- 
cgit v1.2.3


From 94f060e98495e26fd02e18c14e78c61f0d643fd6 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 1 Nov 2019 15:28:08 -0700
Subject: libbpf: Add support for field size relocations

Add bpf_core_field_size() macro, capturing a relocation against field size.
Adjust bits of internal libbpf relocation logic to allow capturing size
relocations of various field types: arrays, structs/unions, enums, etc.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191101222810.1246166-4-andriin@fb.com
---
 tools/lib/bpf/bpf_core_read.h |  7 +++++++
 tools/lib/bpf/libbpf.c        | 40 ++++++++++++++++++++++++++++++++--------
 2 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 0935cd68e7de..11461b2623b0 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -96,6 +96,13 @@ enum bpf_field_info_kind {
 #define bpf_core_field_exists(field)					    \
 	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
 
+/*
+ * Convenience macro to get byte size of a field. Works for integers,
+ * struct/unions, pointers, arrays, and enums.
+ */
+#define bpf_core_field_size(field)					    \
+	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+
 /*
  * bpf_core_read() abstracts away bpf_probe_read() call and captures offset
  * relocation for source address using __builtin_preserve_access_index()
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 482af749f9cf..be4af95d5a2c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2704,8 +2704,10 @@ err_out:
 /* Check two types for compatibility, skipping const/volatile/restrict and
  * typedefs, to ensure we are relocating compatible entities:
  *   - any two STRUCTs/UNIONs are compatible and can be mixed;
- *   - any two FWDs are compatible;
+ *   - any two FWDs are compatible, if their names match (modulo flavor suffix);
  *   - any two PTRs are always compatible;
+ *   - for ENUMs, names should be the same (ignoring flavor suffix) or at
+ *     least one of enums should be anonymous;
  *   - for ENUMs, check sizes, names are ignored;
  *   - for INT, size and signedness are ignored;
  *   - for ARRAY, dimensionality is ignored, element types are checked for
@@ -2733,11 +2735,23 @@ recur:
 		return 0;
 
 	switch (btf_kind(local_type)) {
-	case BTF_KIND_FWD:
 	case BTF_KIND_PTR:
 		return 1;
-	case BTF_KIND_ENUM:
-		return local_type->size == targ_type->size;
+	case BTF_KIND_FWD:
+	case BTF_KIND_ENUM: {
+		const char *local_name, *targ_name;
+		size_t local_len, targ_len;
+
+		local_name = btf__name_by_offset(local_btf,
+						 local_type->name_off);
+		targ_name = btf__name_by_offset(targ_btf, targ_type->name_off);
+		local_len = bpf_core_essential_name_len(local_name);
+		targ_len = bpf_core_essential_name_len(targ_name);
+		/* one of them is anonymous or both w/ same flavor-less names */
+		return local_len == 0 || targ_len == 0 ||
+		       (local_len == targ_len &&
+			strncmp(local_name, targ_name, local_len) == 0);
+	}
 	case BTF_KIND_INT:
 		/* just reject deprecated bitfield-like integers; all other
 		 * integers are by default compatible between each other
@@ -2926,16 +2940,23 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog,
 	const struct btf_member *m;
 	const struct btf_type *mt;
 	bool bitfield;
+	__s64 sz;
 
 	/* a[n] accessor needs special handling */
 	if (!acc->name) {
-		if (relo->kind != BPF_FIELD_BYTE_OFFSET) {
-			pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access'\n",
+		if (relo->kind == BPF_FIELD_BYTE_OFFSET) {
+			*val = spec->bit_offset / 8;
+		} else if (relo->kind == BPF_FIELD_BYTE_SIZE) {
+			sz = btf__resolve_size(spec->btf, acc->type_id);
+			if (sz < 0)
+				return -EINVAL;
+			*val = sz;
+		} else {
+			pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n",
 				bpf_program__title(prog, false),
 				relo->kind, relo->insn_off / 8);
 			return -EINVAL;
 		}
-		*val = spec->bit_offset / 8;
 		if (validate)
 			*validate = true;
 		return 0;
@@ -2963,7 +2984,10 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog,
 			byte_off = bit_off / 8 / byte_sz * byte_sz;
 		}
 	} else {
-		byte_sz = mt->size;
+		sz = btf__resolve_size(spec->btf, m->type);
+		if (sz < 0)
+			return -EINVAL;
+		byte_sz = sz;
 		byte_off = spec->bit_offset / 8;
 		bit_sz = byte_sz * 8;
 	}
-- 
cgit v1.2.3


From 8b1cb1c9601f835c025af5b3cf0e98c8048ad30b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 1 Nov 2019 15:28:09 -0700
Subject: selftest/bpf: Add relocatable bitfield reading tests

Add a bunch of selftests verifying correctness of relocatable bitfield reading
support in libbpf. Both bpf_probe_read()-based and direct read-based bitfield
macros are tested. core_reloc.c "test_harness" is extended to support raw
tracepoint and new typed raw tracepoints as test BPF program types.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191101222810.1246166-5-andriin@fb.com
---
 .../testing/selftests/bpf/prog_tests/core_reloc.c  | 84 +++++++++++++++++++++-
 .../bpf/progs/btf__core_reloc_bitfields.c          |  3 +
 .../btf__core_reloc_bitfields___bit_sz_change.c    |  3 +
 .../btf__core_reloc_bitfields___bitfield_vs_int.c  |  3 +
 ...__core_reloc_bitfields___err_too_big_bitfield.c |  3 +
 .../btf__core_reloc_bitfields___just_big_enough.c  |  3 +
 .../testing/selftests/bpf/progs/core_reloc_types.h | 72 +++++++++++++++++++
 .../bpf/progs/test_core_reloc_bitfields_direct.c   | 63 ++++++++++++++++
 .../bpf/progs/test_core_reloc_bitfields_probed.c   | 62 ++++++++++++++++
 9 files changed, 294 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 09dfa75fe948..340aa12cea06 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -189,6 +189,42 @@
 	.fails = true,							\
 }
 
+#define BITFIELDS_CASE_COMMON(objfile, test_name_prefix,  name)		\
+	.case_name = test_name_prefix#name,				\
+	.bpf_obj_file = objfile,					\
+	.btf_src_file = "btf__core_reloc_" #name ".o"
+
+#define BITFIELDS_CASE(name, ...) {					\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
+			      "direct:", name),				\
+	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) __VA_ARGS__,	\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
+		__VA_ARGS__,						\
+	.output_len = sizeof(struct core_reloc_bitfields_output),	\
+}, {									\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
+			      "probed:", name),				\
+	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) __VA_ARGS__,	\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
+		__VA_ARGS__,						\
+	.output_len = sizeof(struct core_reloc_bitfields_output),	\
+	.direct_raw_tp = true,						\
+}
+
+
+#define BITFIELDS_ERR_CASE(name) {					\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
+			      "probed:", name),				\
+	.fails = true,							\
+}, {									\
+	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
+			      "direct:", name),				\
+	.direct_raw_tp = true,						\
+	.fails = true,							\
+}
+
 struct core_reloc_test_case {
 	const char *case_name;
 	const char *bpf_obj_file;
@@ -199,6 +235,7 @@ struct core_reloc_test_case {
 	int output_len;
 	bool fails;
 	bool relaxed_core_relocs;
+	bool direct_raw_tp;
 };
 
 static struct core_reloc_test_case test_cases[] = {
@@ -352,6 +389,40 @@ static struct core_reloc_test_case test_cases[] = {
 	EXISTENCE_ERR_CASE(existence__err_arr_kind),
 	EXISTENCE_ERR_CASE(existence__err_arr_value_type),
 	EXISTENCE_ERR_CASE(existence__err_struct_type),
+
+	/* bitfield relocation checks */
+	BITFIELDS_CASE(bitfields, {
+		.ub1 = 1,
+		.ub2 = 2,
+		.ub7 = 96,
+		.sb4 = -7,
+		.sb20 = -0x76543,
+		.u32 = 0x80000000,
+		.s32 = -0x76543210,
+	}),
+	BITFIELDS_CASE(bitfields___bit_sz_change, {
+		.ub1 = 6,
+		.ub2 = 0xABCDE,
+		.ub7 = 1,
+		.sb4 = -1,
+		.sb20 = -0x17654321,
+		.u32 = 0xBEEF,
+		.s32 = -0x3FEDCBA987654321,
+	}),
+	BITFIELDS_CASE(bitfields___bitfield_vs_int, {
+		.ub1 = 0xFEDCBA9876543210,
+		.ub2 = 0xA6,
+		.ub7 = -0x7EDCBA987654321,
+		.sb4 = -0x6123456789ABCDE,
+		.sb20 = 0xD00D,
+		.u32 = -0x76543,
+		.s32 = 0x0ADEADBEEFBADB0B,
+	}),
+	BITFIELDS_CASE(bitfields___just_big_enough, {
+		.ub1 = 0xF,
+		.ub2 = 0x0812345678FEDCBA,
+	}),
+	BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield),
 };
 
 struct data {
@@ -361,9 +432,9 @@ struct data {
 
 void test_core_reloc(void)
 {
-	const char *probe_name = "raw_tracepoint/sys_enter";
 	struct bpf_object_load_attr load_attr = {};
 	struct core_reloc_test_case *test_case;
+	const char *tp_name, *probe_name;
 	int err, duration = 0, i, equal;
 	struct bpf_link *link = NULL;
 	struct bpf_map *data_map;
@@ -387,6 +458,15 @@ void test_core_reloc(void)
 			  test_case->bpf_obj_file, PTR_ERR(obj)))
 			continue;
 
+		/* for typed raw tracepoints, NULL should be specified */
+		if (test_case->direct_raw_tp) {
+			probe_name = "tp_btf/sys_enter";
+			tp_name = NULL;
+		} else {
+			probe_name = "raw_tracepoint/sys_enter";
+			tp_name = "sys_enter";
+		}
+
 		prog = bpf_object__find_program_by_title(obj, probe_name);
 		if (CHECK(!prog, "find_probe",
 			  "prog '%s' not found\n", probe_name))
@@ -407,7 +487,7 @@ void test_core_reloc(void)
 				goto cleanup;
 		}
 
-		link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+		link = bpf_program__attach_raw_tracepoint(prog, tp_name);
 		if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n",
 			  PTR_ERR(link)))
 			goto cleanup;
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c
new file mode 100644
index 000000000000..cff6f1836cc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_bitfields x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c
new file mode 100644
index 000000000000..a1cd157d5451
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_bitfields___bit_sz_change x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c
new file mode 100644
index 000000000000..3f2c7b07c456
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_bitfields___bitfield_vs_int x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c
new file mode 100644
index 000000000000..f9746d6be399
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_bitfields___err_too_big_bitfield x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c
new file mode 100644
index 000000000000..e7c75a6953dd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_bitfields___just_big_enough x) {}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 3fe54f6f82cf..7eb08d99ec46 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -662,3 +662,75 @@ struct core_reloc_existence___err_wrong_arr_value_type {
 struct core_reloc_existence___err_wrong_struct_type {
 	int s;
 };
+
+/*
+ * BITFIELDS
+ */
+/* bitfield read results, all as plain integers */
+struct core_reloc_bitfields_output {
+	int64_t		ub1;
+	int64_t		ub2;
+	int64_t		ub7;
+	int64_t		sb4;
+	int64_t		sb20;
+	int64_t		u32;
+	int64_t		s32;
+};
+
+struct core_reloc_bitfields {
+	/* unsigned bitfields */
+	uint8_t		ub1: 1;
+	uint8_t		ub2: 2;
+	uint32_t	ub7: 7;
+	/* signed bitfields */
+	int8_t		sb4: 4;
+	int32_t		sb20: 20;
+	/* non-bitfields */
+	uint32_t	u32;
+	int32_t		s32;
+};
+
+/* different bit sizes (both up and down) */
+struct core_reloc_bitfields___bit_sz_change {
+	/* unsigned bitfields */
+	uint16_t	ub1: 3;		/*  1 ->  3 */
+	uint32_t	ub2: 20;	/*  2 -> 20 */
+	uint8_t		ub7: 1;		/*  7 ->  1 */
+	/* signed bitfields */
+	int8_t		sb4: 1;		/*  4 ->  1 */
+	int32_t		sb20: 30;	/* 20 -> 30 */
+	/* non-bitfields */
+	uint16_t	u32;		/* 32 -> 16 */
+	int64_t		s32;		/* 32 -> 64 */
+};
+
+/* turn bitfield into non-bitfield and vice versa */
+struct core_reloc_bitfields___bitfield_vs_int {
+	uint64_t	ub1;		/*  3 -> 64 non-bitfield */
+	uint8_t		ub2;		/* 20 ->  8 non-bitfield */
+	int64_t		ub7;		/*  7 -> 64 non-bitfield signed */
+	int64_t		sb4;		/*  4 -> 64 non-bitfield signed */
+	uint64_t	sb20;		/* 20 -> 16 non-bitfield unsigned */
+	int32_t		u32: 20;	/* 32 non-bitfield -> 20 bitfield */
+	uint64_t	s32: 60;	/* 32 non-bitfield -> 60 bitfield */
+};
+
+struct core_reloc_bitfields___just_big_enough {
+	uint64_t	ub1: 4;
+	uint64_t	ub2: 60; /* packed tightly */
+	uint32_t	ub7;
+	uint32_t	sb4;
+	uint32_t	sb20;
+	uint32_t	u32;
+	uint32_t	s32;
+} __attribute__((packed)) ;
+
+struct core_reloc_bitfields___err_too_big_bitfield {
+	uint64_t	ub1: 4;
+	uint64_t	ub2: 61; /* packed tightly */
+	uint32_t	ub7;
+	uint32_t	sb4;
+	uint32_t	sb20;
+	uint32_t	u32;
+	uint32_t	s32;
+} __attribute__((packed)) ;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
new file mode 100644
index 000000000000..738b34b72655
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include "bpf_helpers.h"
+#include "bpf_core_read.h"
+
+char _license[] SEC("license") = "GPL";
+
+static volatile struct data {
+	char in[256];
+	char out[256];
+} data;
+
+struct core_reloc_bitfields {
+	/* unsigned bitfields */
+	uint8_t		ub1: 1;
+	uint8_t		ub2: 2;
+	uint32_t	ub7: 7;
+	/* signed bitfields */
+	int8_t		sb4: 4;
+	int32_t		sb20: 20;
+	/* non-bitfields */
+	uint32_t	u32;
+	int32_t		s32;
+};
+
+/* bitfield read results, all as plain integers */
+struct core_reloc_bitfields_output {
+	int64_t		ub1;
+	int64_t		ub2;
+	int64_t		ub7;
+	int64_t		sb4;
+	int64_t		sb20;
+	int64_t		u32;
+	int64_t		s32;
+};
+
+struct pt_regs;
+
+struct trace_sys_enter {
+	struct pt_regs *regs;
+	long id;
+};
+
+SEC("tp_btf/sys_enter")
+int test_core_bitfields_direct(void *ctx)
+{
+	struct core_reloc_bitfields *in = (void *)&data.in;
+	struct core_reloc_bitfields_output *out = (void *)&data.out;
+
+	out->ub1 = BPF_CORE_READ_BITFIELD(in, ub1);
+	out->ub2 = BPF_CORE_READ_BITFIELD(in, ub2);
+	out->ub7 = BPF_CORE_READ_BITFIELD(in, ub7);
+	out->sb4 = BPF_CORE_READ_BITFIELD(in, sb4);
+	out->sb20 = BPF_CORE_READ_BITFIELD(in, sb20);
+	out->u32 = BPF_CORE_READ_BITFIELD(in, u32);
+	out->s32 = BPF_CORE_READ_BITFIELD(in, s32);
+
+	return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
new file mode 100644
index 000000000000..a381f8ac2419
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include "bpf_helpers.h"
+#include "bpf_core_read.h"
+
+char _license[] SEC("license") = "GPL";
+
+static volatile struct data {
+	char in[256];
+	char out[256];
+} data;
+
+struct core_reloc_bitfields {
+	/* unsigned bitfields */
+	uint8_t		ub1: 1;
+	uint8_t		ub2: 2;
+	uint32_t	ub7: 7;
+	/* signed bitfields */
+	int8_t		sb4: 4;
+	int32_t		sb20: 20;
+	/* non-bitfields */
+	uint32_t	u32;
+	int32_t		s32;
+};
+
+/* bitfield read results, all as plain integers */
+struct core_reloc_bitfields_output {
+	int64_t		ub1;
+	int64_t		ub2;
+	int64_t		ub7;
+	int64_t		sb4;
+	int64_t		sb20;
+	int64_t		u32;
+	int64_t		s32;
+};
+
+#define TRANSFER_BITFIELD(in, out, field)				\
+	if (BPF_CORE_READ_BITFIELD_PROBED(in, field, &res))		\
+		return 1;						\
+	out->field = res
+
+SEC("raw_tracepoint/sys_enter")
+int test_core_bitfields(void *ctx)
+{
+	struct core_reloc_bitfields *in = (void *)&data.in;
+	struct core_reloc_bitfields_output *out = (void *)&data.out;
+	uint64_t res;
+
+	TRANSFER_BITFIELD(in, out, ub1);
+	TRANSFER_BITFIELD(in, out, ub2);
+	TRANSFER_BITFIELD(in, out, ub7);
+	TRANSFER_BITFIELD(in, out, sb4);
+	TRANSFER_BITFIELD(in, out, sb20);
+	TRANSFER_BITFIELD(in, out, u32);
+	TRANSFER_BITFIELD(in, out, s32);
+
+	return 0;
+}
+
-- 
cgit v1.2.3


From 0b163565b918fd5ad1cf8ab7a92cffa06c13b204 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 1 Nov 2019 15:28:10 -0700
Subject: selftests/bpf: Add field size relocation tests

Add test verifying correctness and logic of field size relocation support in
libbpf.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191101222810.1246166-6-andriin@fb.com
---
 .../testing/selftests/bpf/prog_tests/core_reloc.c  | 39 ++++++++++++++---
 .../selftests/bpf/progs/btf__core_reloc_size.c     |  3 ++
 .../bpf/progs/btf__core_reloc_size___diff_sz.c     |  3 ++
 .../testing/selftests/bpf/progs/core_reloc_types.h | 31 +++++++++++++
 .../selftests/bpf/progs/test_core_reloc_size.c     | 51 ++++++++++++++++++++++
 5 files changed, 122 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_size.c
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_core_reloc_size.c

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 340aa12cea06..00f1f3229542 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -174,15 +174,11 @@
 	.fails = true,							\
 }
 
-#define EXISTENCE_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
-	.a = 42,							\
-}
-
 #define EXISTENCE_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_existence.o",			\
 	.btf_src_file = "btf__core_reloc_" #name ".o",			\
-	.relaxed_core_relocs = true					\
+	.relaxed_core_relocs = true
 
 #define EXISTENCE_ERR_CASE(name) {					\
 	EXISTENCE_CASE_COMMON(name),					\
@@ -225,6 +221,35 @@
 	.fails = true,							\
 }
 
+#define SIZE_CASE_COMMON(name)						\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_size.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.relaxed_core_relocs = true
+
+#define SIZE_OUTPUT_DATA(type)						\
+	STRUCT_TO_CHAR_PTR(core_reloc_size_output) {			\
+		.int_sz = sizeof(((type *)0)->int_field),		\
+		.struct_sz = sizeof(((type *)0)->struct_field),		\
+		.union_sz = sizeof(((type *)0)->union_field),		\
+		.arr_sz = sizeof(((type *)0)->arr_field),		\
+		.arr_elem_sz = sizeof(((type *)0)->arr_field[0]),	\
+		.ptr_sz = sizeof(((type *)0)->ptr_field),		\
+		.enum_sz = sizeof(((type *)0)->enum_field),	\
+	}
+
+#define SIZE_CASE(name) {						\
+	SIZE_CASE_COMMON(name),						\
+	.input_len = 0,							\
+	.output = SIZE_OUTPUT_DATA(struct core_reloc_##name),		\
+	.output_len = sizeof(struct core_reloc_size_output),		\
+}
+
+#define SIZE_ERR_CASE(name) {						\
+	SIZE_CASE_COMMON(name),						\
+	.fails = true,							\
+}
+
 struct core_reloc_test_case {
 	const char *case_name;
 	const char *bpf_obj_file;
@@ -423,6 +448,10 @@ static struct core_reloc_test_case test_cases[] = {
 		.ub2 = 0x0812345678FEDCBA,
 	}),
 	BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield),
+
+	/* size relocation checks */
+	SIZE_CASE(size),
+	SIZE_CASE(size___diff_sz),
 };
 
 struct data {
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size.c
new file mode 100644
index 000000000000..3c80903da5a4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_size x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c
new file mode 100644
index 000000000000..6dbd14436b52
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_size___diff_sz x) {}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 7eb08d99ec46..9311489e14b2 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -734,3 +734,34 @@ struct core_reloc_bitfields___err_too_big_bitfield {
 	uint32_t	u32;
 	uint32_t	s32;
 } __attribute__((packed)) ;
+
+/*
+ * SIZE
+ */
+struct core_reloc_size_output {
+	int int_sz;
+	int struct_sz;
+	int union_sz;
+	int arr_sz;
+	int arr_elem_sz;
+	int ptr_sz;
+	int enum_sz;
+};
+
+struct core_reloc_size {
+	int int_field;
+	struct { int x; } struct_field;
+	union { int x; } union_field;
+	int arr_field[4];
+	void *ptr_field;
+	enum { VALUE = 123 } enum_field;
+};
+
+struct core_reloc_size___diff_sz {
+	uint64_t int_field;
+	struct { int x; int y; int z; } struct_field;
+	union { int x; char bla[123]; } union_field;
+	char arr_field[10];
+	void *ptr_field;
+	enum { OTHER_VALUE = 0xFFFFFFFFFFFFFFFF } enum_field;
+};
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
new file mode 100644
index 000000000000..9a92998d9107
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include "bpf_helpers.h"
+#include "bpf_core_read.h"
+
+char _license[] SEC("license") = "GPL";
+
+static volatile struct data {
+	char in[256];
+	char out[256];
+} data;
+
+struct core_reloc_size_output {
+	int int_sz;
+	int struct_sz;
+	int union_sz;
+	int arr_sz;
+	int arr_elem_sz;
+	int ptr_sz;
+	int enum_sz;
+};
+
+struct core_reloc_size {
+	int int_field;
+	struct { int x; } struct_field;
+	union { int x; } union_field;
+	int arr_field[4];
+	void *ptr_field;
+	enum { VALUE = 123 } enum_field;
+};
+
+SEC("raw_tracepoint/sys_enter")
+int test_core_size(void *ctx)
+{
+	struct core_reloc_size *in = (void *)&data.in;
+	struct core_reloc_size_output *out = (void *)&data.out;
+
+	out->int_sz = bpf_core_field_size(in->int_field);
+	out->struct_sz = bpf_core_field_size(in->struct_field);
+	out->union_sz = bpf_core_field_size(in->union_field);
+	out->arr_sz = bpf_core_field_size(in->arr_field);
+	out->arr_elem_sz = bpf_core_field_size(in->arr_field[0]);
+	out->ptr_sz = bpf_core_field_size(in->ptr_field);
+	out->enum_sz = bpf_core_field_size(in->enum_field);
+
+	return 0;
+}
+
-- 
cgit v1.2.3


From 65a052d537f40e992eb1629cc6c25874064f51fd Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 09:36:59 -0800
Subject: selftests/bps: Clean up removed ints relocations negative tests

As part of 42765ede5c54 ("selftests/bpf: Remove too strict field offset relo
test cases"), few ints relocations negative (supposed to fail) tests were
removed, but not completely. Due to them being negative, some leftovers in
prog_tests/core_reloc.c went unnoticed. Clean them up.

Fixes: 42765ede5c54 ("selftests/bpf: Remove too strict field offset relo test cases")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191106173659.1978131-1-andriin@fb.com
---
 tools/testing/selftests/bpf/prog_tests/core_reloc.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 00f1f3229542..f94bd071536b 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -337,12 +337,6 @@ static struct core_reloc_test_case test_cases[] = {
 	INTS_CASE(ints___bool),
 	INTS_CASE(ints___reverse_sign),
 
-	INTS_ERR_CASE(ints___err_bitfield),
-	INTS_ERR_CASE(ints___err_wrong_sz_8),
-	INTS_ERR_CASE(ints___err_wrong_sz_16),
-	INTS_ERR_CASE(ints___err_wrong_sz_32),
-	INTS_ERR_CASE(ints___err_wrong_sz_64),
-	
 	/* validate edge cases of capturing relocations */
 	{
 		.case_name = "misc",
-- 
cgit v1.2.3


From ed578021210e14f15a654c825fba6a700c9a39a7 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 12:15:00 -0800
Subject: libbpf: Simplify BPF_CORE_READ_BITFIELD_PROBED usage

Streamline BPF_CORE_READ_BITFIELD_PROBED interface to follow
BPF_CORE_READ_BITFIELD (direct) and BPF_CORE_READ, in general, i.e., just
return read result or 0, if underlying bpf_probe_read() failed.

In practice, real applications rarely check bpf_probe_read() result, because
it has to always work or otherwise it's a bug. So propagating internal
bpf_probe_read() error from this macro hurts usability without providing real
benefits in practice. This patch fixes the issue and simplifies usage,
noticeable even in selftest itself.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20191106201500.2582438-1-andriin@fb.com
---
 tools/lib/bpf/bpf_core_read.h                      | 27 +++++++++-------------
 .../bpf/progs/test_core_reloc_bitfields_probed.c   | 19 ++++++---------
 2 files changed, 18 insertions(+), 28 deletions(-)

diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 11461b2623b0..7009dc90e012 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -39,32 +39,27 @@ enum bpf_field_info_kind {
 #endif
 
 /*
- * Extract bitfield, identified by src->field, and put its value into u64
- * *res. All this is done in relocatable manner, so bitfield changes such as
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * All this is done in relocatable manner, so bitfield changes such as
  * signedness, bit size, offset changes, this will be handled automatically.
  * This version of macro is using bpf_probe_read() to read underlying integer
  * storage. Macro functions as an expression and its return type is
  * bpf_probe_read()'s return value: 0, on success, <0 on error.
  */
-#define BPF_CORE_READ_BITFIELD_PROBED(src, field, res) ({		      \
-	unsigned long long val;						      \
+#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({			      \
+	unsigned long long val = 0;					      \
 									      \
-	*res = 0;							      \
-	val = __CORE_BITFIELD_PROBE_READ(res, src, field);		      \
-	if (!val) {							      \
-		*res <<= __CORE_RELO(src, field, LSHIFT_U64);		      \
-		val = __CORE_RELO(src, field, RSHIFT_U64);		      \
-		if (__CORE_RELO(src, field, SIGNED))			      \
-			*res = ((long long)*res) >> val;		      \
-		else							      \
-			*res = ((unsigned long long)*res) >> val;	      \
-		val = 0;						      \
-	}								      \
+	__CORE_BITFIELD_PROBE_READ(&val, s, field);			      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
 	val;								      \
 })
 
 /*
- * Extract bitfield, identified by src->field, and return its value as u64.
+ * Extract bitfield, identified by s->field, and return its value as u64.
  * This version of macro is using direct memory reads and should be used from
  * BPF program types that support such functionality (e.g., typed raw
  * tracepoints).
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
index a381f8ac2419..e466e3ab7de4 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
@@ -37,11 +37,6 @@ struct core_reloc_bitfields_output {
 	int64_t		s32;
 };
 
-#define TRANSFER_BITFIELD(in, out, field)				\
-	if (BPF_CORE_READ_BITFIELD_PROBED(in, field, &res))		\
-		return 1;						\
-	out->field = res
-
 SEC("raw_tracepoint/sys_enter")
 int test_core_bitfields(void *ctx)
 {
@@ -49,13 +44,13 @@ int test_core_bitfields(void *ctx)
 	struct core_reloc_bitfields_output *out = (void *)&data.out;
 	uint64_t res;
 
-	TRANSFER_BITFIELD(in, out, ub1);
-	TRANSFER_BITFIELD(in, out, ub2);
-	TRANSFER_BITFIELD(in, out, ub7);
-	TRANSFER_BITFIELD(in, out, sb4);
-	TRANSFER_BITFIELD(in, out, sb20);
-	TRANSFER_BITFIELD(in, out, u32);
-	TRANSFER_BITFIELD(in, out, s32);
+	out->ub1 = BPF_CORE_READ_BITFIELD_PROBED(in, ub1);
+	out->ub2 = BPF_CORE_READ_BITFIELD_PROBED(in, ub2);
+	out->ub7 = BPF_CORE_READ_BITFIELD_PROBED(in, ub7);
+	out->sb4 = BPF_CORE_READ_BITFIELD_PROBED(in, sb4);
+	out->sb20 = BPF_CORE_READ_BITFIELD_PROBED(in, sb20);
+	out->u32 = BPF_CORE_READ_BITFIELD_PROBED(in, u32);
+	out->s32 = BPF_CORE_READ_BITFIELD_PROBED(in, s32);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 85d31dd07002315c0d1816543fdc392c8cc6b73a Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 6 Nov 2019 17:46:40 -0800
Subject: bpf: Account for insn->off when doing bpf_probe_read_kernel

In the bpf interpreter mode, bpf_probe_read_kernel is used to read
from PTR_TO_BTF_ID's kernel object.  It currently missed considering
the insn->off.  This patch fixes it.

Fixes: 2a02759ef5f8 ("bpf: Add support for BTF pointers to interpreter")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191107014640.384083-1-kafai@fb.com
---
 kernel/bpf/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 97e37d82a1cc..c1fde0303280 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1569,7 +1569,7 @@ out:
 #undef LDST
 #define LDX_PROBE(SIZEOP, SIZE)							\
 	LDX_PROBE_MEM_##SIZEOP:							\
-		bpf_probe_read_kernel(&DST, SIZE, (const void *)(long) SRC);	\
+		bpf_probe_read_kernel(&DST, SIZE, (const void *)(long) (SRC + insn->off));	\
 		CONT;
 	LDX_PROBE(B,  1)
 	LDX_PROBE(H,  2)
-- 
cgit v1.2.3


From 7e22077d0c73a68ff3fd8b3d2f6564fcbcf8cb23 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 7 Nov 2019 11:03:49 +0100
Subject: tools, bpf_asm: Warn when jumps are out of range

When compiling larger programs with bpf_asm, it's possible to
accidentally exceed jt/jf range, in which case it won't complain, but
rather silently emit a truncated offset, leading to a "happy debugging"
situation.

Add a warning to help detecting such issues. It could be made an error
instead, but this might break compilation of existing code (which might
be working by accident).

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107100349.88976-1-iii@linux.ibm.com
---
 tools/bpf/bpf_exp.y | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/bpf_exp.y b/tools/bpf/bpf_exp.y
index 56ba1de50784..8d48e896be50 100644
--- a/tools/bpf/bpf_exp.y
+++ b/tools/bpf/bpf_exp.y
@@ -545,6 +545,16 @@ static void bpf_reduce_k_jumps(void)
 	}
 }
 
+static uint8_t bpf_encode_jt_jf_offset(int off, int i)
+{
+	int delta = off - i - 1;
+
+	if (delta < 0 || delta > 255)
+		fprintf(stderr, "warning: insn #%d jumps to insn #%d, "
+				"which is out of range\n", i, off);
+	return (uint8_t) delta;
+}
+
 static void bpf_reduce_jt_jumps(void)
 {
 	int i;
@@ -552,7 +562,7 @@ static void bpf_reduce_jt_jumps(void)
 	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);
+			out[i].jt = bpf_encode_jt_jf_offset(off, i);
 		}
 	}
 }
@@ -564,7 +574,7 @@ static void bpf_reduce_jf_jumps(void)
 	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);
+			out[i].jf = bpf_encode_jt_jf_offset(off, i);
 		}
 	}
 }
-- 
cgit v1.2.3


From 166f11d11f6f70439830d09bfa5552ec1b368494 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 7 Nov 2019 15:18:38 +0100
Subject: s390/bpf: Use kvcalloc for addrs array

A BPF program may consist of 1m instructions, which means JIT
instruction-address mapping can be as large as 4m. s390 has
FORCE_MAX_ZONEORDER=9 (for memory hotplug reasons), which means maximum
kmalloc size is 1m. This makes it impossible to JIT programs with more
than 256k instructions.

Fix by using kvcalloc, which falls back to vmalloc for larger
allocations. An alternative would be to use a radix tree, but that is
not supported by bpf_prog_fill_jited_linfo.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107141838.92202-1-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index ce88211b9c6c..c8c16b5eed6b 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -23,6 +23,7 @@
 #include <linux/filter.h>
 #include <linux/init.h>
 #include <linux/bpf.h>
+#include <linux/mm.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
 #include <asm/facility.h>
@@ -1369,7 +1370,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	memset(&jit, 0, sizeof(jit));
-	jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
+	jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
 	if (jit.addrs == NULL) {
 		fp = orig_fp;
 		goto out;
@@ -1422,7 +1423,7 @@ skip_init_ctx:
 	if (!fp->is_func || extra_pass) {
 		bpf_prog_fill_jited_linfo(fp, jit.addrs + 1);
 free_addrs:
-		kfree(jit.addrs);
+		kvfree(jit.addrs);
 		kfree(jit_data);
 		fp->aux->jit_data = NULL;
 	}
-- 
cgit v1.2.3


From 6ad2e1a00729f9a27b80f8d9962520b89420280d Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 7 Nov 2019 12:32:11 +0100
Subject: s390/bpf: Wrap JIT macro parameter usages in parentheses

This change does not alter JIT behavior; it only makes it possible to
safely invoke JIT macros with complex arguments in the future.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107113211.90105-1-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 62 ++++++++++++++++++++++----------------------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index c8c16b5eed6b..35661c2b736e 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -132,13 +132,13 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT2(op)						\
 ({								\
 	if (jit->prg_buf)					\
-		*(u16 *) (jit->prg_buf + jit->prg) = op;	\
+		*(u16 *) (jit->prg_buf + jit->prg) = (op);	\
 	jit->prg += 2;						\
 })
 
 #define EMIT2(op, b1, b2)					\
 ({								\
-	_EMIT2(op | reg(b1, b2));				\
+	_EMIT2((op) | reg(b1, b2));				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
@@ -146,20 +146,20 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT4(op)						\
 ({								\
 	if (jit->prg_buf)					\
-		*(u32 *) (jit->prg_buf + jit->prg) = op;	\
+		*(u32 *) (jit->prg_buf + jit->prg) = (op);	\
 	jit->prg += 4;						\
 })
 
 #define EMIT4(op, b1, b2)					\
 ({								\
-	_EMIT4(op | reg(b1, b2));				\
+	_EMIT4((op) | reg(b1, b2));				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
 
 #define EMIT4_RRF(op, b1, b2, b3)				\
 ({								\
-	_EMIT4(op | reg_high(b3) << 8 | reg(b1, b2));		\
+	_EMIT4((op) | reg_high(b3) << 8 | reg(b1, b2));		\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 	REG_SET_SEEN(b3);					\
@@ -168,13 +168,13 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT4_DISP(op, disp)					\
 ({								\
 	unsigned int __disp = (disp) & 0xfff;			\
-	_EMIT4(op | __disp);					\
+	_EMIT4((op) | __disp);					\
 })
 
 #define EMIT4_DISP(op, b1, b2, disp)				\
 ({								\
-	_EMIT4_DISP(op | reg_high(b1) << 16 |			\
-		    reg_high(b2) << 8, disp);			\
+	_EMIT4_DISP((op) | reg_high(b1) << 16 |			\
+		    reg_high(b2) << 8, (disp));			\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
@@ -182,21 +182,21 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT4_IMM(op, b1, imm)					\
 ({								\
 	unsigned int __imm = (imm) & 0xffff;			\
-	_EMIT4(op | reg_high(b1) << 16 | __imm);		\
+	_EMIT4((op) | reg_high(b1) << 16 | __imm);		\
 	REG_SET_SEEN(b1);					\
 })
 
 #define EMIT4_PCREL(op, pcrel)					\
 ({								\
 	long __pcrel = ((pcrel) >> 1) & 0xffff;			\
-	_EMIT4(op | __pcrel);					\
+	_EMIT4((op) | __pcrel);					\
 })
 
 #define _EMIT6(op1, op2)					\
 ({								\
 	if (jit->prg_buf) {					\
-		*(u32 *) (jit->prg_buf + jit->prg) = op1;	\
-		*(u16 *) (jit->prg_buf + jit->prg + 4) = op2;	\
+		*(u32 *) (jit->prg_buf + jit->prg) = (op1);	\
+		*(u16 *) (jit->prg_buf + jit->prg + 4) = (op2);	\
 	}							\
 	jit->prg += 6;						\
 })
@@ -204,20 +204,20 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT6_DISP(op1, op2, disp)				\
 ({								\
 	unsigned int __disp = (disp) & 0xfff;			\
-	_EMIT6(op1 | __disp, op2);				\
+	_EMIT6((op1) | __disp, op2);				\
 })
 
 #define _EMIT6_DISP_LH(op1, op2, disp)				\
 ({								\
-	u32 _disp = (u32) disp;					\
+	u32 _disp = (u32) (disp);				\
 	unsigned int __disp_h = _disp & 0xff000;		\
 	unsigned int __disp_l = _disp & 0x00fff;		\
-	_EMIT6(op1 | __disp_l, op2 | __disp_h >> 4);		\
+	_EMIT6((op1) | __disp_l, (op2) | __disp_h >> 4);	\
 })
 
 #define EMIT6_DISP_LH(op1, op2, b1, b2, b3, disp)		\
 ({								\
-	_EMIT6_DISP_LH(op1 | reg(b1, b2) << 16 |		\
+	_EMIT6_DISP_LH((op1) | reg(b1, b2) << 16 |		\
 		       reg_high(b3) << 8, op2, disp);		\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
@@ -227,8 +227,8 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask)	\
 ({								\
 	int rel = (jit->labels[label] - jit->prg) >> 1;		\
-	_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff),	\
-	       op2 | mask << 12);				\
+	_EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff),	\
+	       (op2) | (mask) << 12);				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
@@ -236,43 +236,43 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask)	\
 ({								\
 	int rel = (jit->labels[label] - jit->prg) >> 1;		\
-	_EMIT6(op1 | (reg_high(b1) | mask) << 16 |		\
-		(rel & 0xffff), op2 | (imm & 0xff) << 8);	\
+	_EMIT6((op1) | (reg_high(b1) | (mask)) << 16 |		\
+		(rel & 0xffff), (op2) | ((imm) & 0xff) << 8);	\
 	REG_SET_SEEN(b1);					\
-	BUILD_BUG_ON(((unsigned long) imm) > 0xff);		\
+	BUILD_BUG_ON(((unsigned long) (imm)) > 0xff);		\
 })
 
 #define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask)		\
 ({								\
 	/* Branch instruction needs 6 bytes */			\
-	int rel = (addrs[i + off + 1] - (addrs[i + 1] - 6)) / 2;\
-	_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), op2 | mask);	\
+	int rel = (addrs[(i) + (off) + 1] - (addrs[(i) + 1] - 6)) / 2;\
+	_EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff), (op2) | (mask));\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
 
 #define EMIT6_PCREL_RILB(op, b, target)				\
 ({								\
-	int rel = (target - jit->prg) / 2;			\
-	_EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff);	\
+	int rel = ((target) - jit->prg) / 2;			\
+	_EMIT6((op) | reg_high(b) << 16 | rel >> 16, rel & 0xffff);\
 	REG_SET_SEEN(b);					\
 })
 
 #define EMIT6_PCREL_RIL(op, target)				\
 ({								\
-	int rel = (target - jit->prg) / 2;			\
-	_EMIT6(op | rel >> 16, rel & 0xffff);			\
+	int rel = ((target) - jit->prg) / 2;			\
+	_EMIT6((op) | rel >> 16, rel & 0xffff);			\
 })
 
 #define _EMIT6_IMM(op, imm)					\
 ({								\
 	unsigned int __imm = (imm);				\
-	_EMIT6(op | (__imm >> 16), __imm & 0xffff);		\
+	_EMIT6((op) | (__imm >> 16), __imm & 0xffff);		\
 })
 
 #define EMIT6_IMM(op, b1, imm)					\
 ({								\
-	_EMIT6_IMM(op | reg_high(b1) << 16, imm);		\
+	_EMIT6_IMM((op) | reg_high(b1) << 16, imm);		\
 	REG_SET_SEEN(b1);					\
 })
 
@@ -282,7 +282,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	ret = jit->lit - jit->base_ip;				\
 	jit->seen |= SEEN_LITERAL;				\
 	if (jit->prg_buf)					\
-		*(u32 *) (jit->prg_buf + jit->lit) = (u32) val;	\
+		*(u32 *) (jit->prg_buf + jit->lit) = (u32) (val);\
 	jit->lit += 4;						\
 	ret;							\
 })
@@ -293,7 +293,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	ret = jit->lit - jit->base_ip;				\
 	jit->seen |= SEEN_LITERAL;				\
 	if (jit->prg_buf)					\
-		*(u64 *) (jit->prg_buf + jit->lit) = (u64) val;	\
+		*(u64 *) (jit->prg_buf + jit->lit) = (u64) (val);\
 	jit->lit += 8;						\
 	ret;							\
 })
-- 
cgit v1.2.3


From dab2e9eb187cb53c951c0c556172a73ac7f0e834 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 7 Nov 2019 12:40:33 +0100
Subject: s390/bpf: Remove unused SEEN_RET0, SEEN_REG_AX and ret0_ip

We don't need them since commit e1cf4befa297 ("bpf, s390x: remove
ld_abs/ld_ind") and commit a3212b8f15d8 ("bpf, s390x: remove obsolete
exception handling from div/mod").

Also, use BIT(n) instead of 1 << n, because checkpatch says so.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107114033.90505-1-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 35661c2b736e..1115071c8ff7 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -42,7 +42,6 @@ struct bpf_jit {
 	int lit_start;		/* Start of literal pool */
 	int lit;		/* Current position in literal pool */
 	int base_ip;		/* Base address for literal pool */
-	int ret0_ip;		/* Address of return 0 */
 	int exit_ip;		/* Address of exit */
 	int r1_thunk_ip;	/* Address of expoline thunk for 'br %r1' */
 	int r14_thunk_ip;	/* Address of expoline thunk for 'br %r14' */
@@ -52,12 +51,10 @@ struct bpf_jit {
 
 #define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
 
-#define SEEN_MEM	(1 << 0)	/* use mem[] for temporary storage */
-#define SEEN_RET0	(1 << 1)	/* ret0_ip points to a valid return 0 */
-#define SEEN_LITERAL	(1 << 2)	/* code uses literals */
-#define SEEN_FUNC	(1 << 3)	/* calls C functions */
-#define SEEN_TAIL_CALL	(1 << 4)	/* code uses tail calls */
-#define SEEN_REG_AX	(1 << 5)	/* code uses constant blinding */
+#define SEEN_MEM	BIT(0)		/* use mem[] for temporary storage */
+#define SEEN_LITERAL	BIT(1)		/* code uses literals */
+#define SEEN_FUNC	BIT(2)		/* calls C functions */
+#define SEEN_TAIL_CALL	BIT(3)		/* code uses tail calls */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM)
 
 /*
@@ -447,12 +444,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
  */
 static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 {
-	/* Return 0 */
-	if (jit->seen & SEEN_RET0) {
-		jit->ret0_ip = jit->prg;
-		/* lghi %b0,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_0, 0);
-	}
 	jit->exit_ip = jit->prg;
 	/* Load exit code: lgr %r2,%b0 */
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
@@ -515,8 +506,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 	s16 off = insn->off;
 	unsigned int mask;
 
-	if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
-		jit->seen |= SEEN_REG_AX;
 	switch (insn->code) {
 	/*
 	 * BPF_MOV
@@ -1111,7 +1100,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		break;
 	case BPF_JMP | BPF_EXIT: /* return b0 */
 		last = (i == fp->len - 1) ? 1 : 0;
-		if (last && !(jit->seen & SEEN_RET0))
+		if (last)
 			break;
 		/* j <exit> */
 		EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg);
-- 
cgit v1.2.3


From 9656b346b280c3e49c8a116c3a715f966633b161 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 21:40:59 -0800
Subject: libbpf: Fix negative FD close() in xsk_setup_xdp_prog()

Fix issue reported by static analysis (Coverity). If bpf_prog_get_fd_by_id()
fails, xsk_lookup_bpf_maps() will fail as well and clean-up code will attempt
close() with fd=-1. Fix by checking bpf_prog_get_fd_by_id() return result and
exiting early.

Fixes: 10a13bb40e54 ("libbpf: remove qidconf and better support external bpf programs.")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107054059.313884-1-andriin@fb.com
---
 tools/lib/bpf/xsk.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 74d84f36a5b2..86c1b61017f6 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -553,6 +553,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	} else {
 		xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
+		if (xsk->prog_fd < 0)
+			return -errno;
 		err = xsk_lookup_bpf_maps(xsk);
 		if (err) {
 			close(xsk->prog_fd);
-- 
cgit v1.2.3


From 3dc5e059821376974177cc801d377e3fcdac6712 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 18:08:51 -0800
Subject: libbpf: Fix memory leak/double free issue

Coverity scan against Github libbpf code found the issue of not freeing memory and
leaving already freed memory still referenced from bpf_program. Fix it by
re-assigning successfully reallocated memory sooner.

Fixes: 2993e0515bb4 ("tools/bpf: add support to read .BTF.ext sections")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107020855.3834758-2-andriin@fb.com
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index be4af95d5a2c..3ef73a214592 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3523,6 +3523,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			pr_warn("oom in prog realloc\n");
 			return -ENOMEM;
 		}
+		prog->insns = new_insn;
 
 		if (obj->btf_ext) {
 			err = bpf_program_reloc_btf_ext(prog, obj,
@@ -3534,7 +3535,6 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 
 		memcpy(new_insn + prog->insns_cnt, text->insns,
 		       text->insns_cnt * sizeof(*insn));
-		prog->insns = new_insn;
 		prog->main_prog_cnt = prog->insns_cnt;
 		prog->insns_cnt = new_cnt;
 		pr_debug("added %zd insn from %s to prog %s\n",
-- 
cgit v1.2.3


From 4ee1135615713387b869dfd099ffdf8656be6784 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 18:08:52 -0800
Subject: libbpf: Fix potential overflow issue

Fix a potential overflow issue found by LGTM analysis, based on Github libbpf
source code.

Fixes: 3d65014146c6 ("bpf: libbpf: Add btf_line_info support to libbpf")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107020855.3834758-3-andriin@fb.com
---
 tools/lib/bpf/bpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ca0d635b1d5e..b3e3e99a0f28 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -189,7 +189,7 @@ static void *
 alloc_zero_tailing_info(const void *orecord, __u32 cnt,
 			__u32 actual_rec_size, __u32 expected_rec_size)
 {
-	__u64 info_len = actual_rec_size * cnt;
+	__u64 info_len = (__u64)actual_rec_size * cnt;
 	void *info, *nrecord;
 	int i;
 
-- 
cgit v1.2.3


From dd3ab126379ec040b3edab8559f9c72de6ef9d29 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 18:08:53 -0800
Subject: libbpf: Fix another potential overflow issue in bpf_prog_linfo

Fix few issues found by Coverity and LGTM.

Fixes: b053b439b72a ("bpf: libbpf: bpftool: Print bpf_line_info during prog dump")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107020855.3834758-4-andriin@fb.com
---
 tools/lib/bpf/bpf_prog_linfo.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 8c67561c93b0..3ed1a27b5f7c 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -101,6 +101,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 {
 	struct bpf_prog_linfo *prog_linfo;
 	__u32 nr_linfo, nr_jited_func;
+	__u64 data_sz;
 
 	nr_linfo = info->nr_line_info;
 
@@ -122,11 +123,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
 	prog_linfo->rec_size = info->line_info_rec_size;
-	prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->rec_size;
+	prog_linfo->raw_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_linfo)
 		goto err_free;
-	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
-	       nr_linfo * prog_linfo->rec_size);
+	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz);
 
 	nr_jited_func = info->nr_jited_ksyms;
 	if (!nr_jited_func ||
@@ -142,13 +143,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy jited_line_info */
 	prog_linfo->nr_jited_func = nr_jited_func;
 	prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
-	prog_linfo->raw_jited_linfo = malloc(nr_linfo *
-					     prog_linfo->jited_rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size;
+	prog_linfo->raw_jited_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_jited_linfo)
 		goto err_free;
 	memcpy(prog_linfo->raw_jited_linfo,
-	       (void *)(long)info->jited_line_info,
-	       nr_linfo * prog_linfo->jited_rec_size);
+	       (void *)(long)info->jited_line_info, data_sz);
 
 	/* Number of jited_line_info per jited func */
 	prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
-- 
cgit v1.2.3


From 994021a7e08477f7e51285920aac99fc967fae8a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 18:08:54 -0800
Subject: libbpf: Make btf__resolve_size logic always check size error
 condition

Perform size check always in btf__resolve_size. Makes the logic a bit more
robust against corrupted BTF and silences LGTM/Coverity complaining about
always true (size < 0) check.

Fixes: 69eaab04c675 ("btf: extract BTF type size calculation")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107020855.3834758-5-andriin@fb.com
---
 tools/lib/bpf/btf.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d72e9a79dce1..86a1847e4a9f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -269,10 +269,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		t = btf__type_by_id(btf, type_id);
 	}
 
+done:
 	if (size < 0)
 		return -EINVAL;
-
-done:
 	if (nelems && size > UINT32_MAX / nelems)
 		return -E2BIG;
 
-- 
cgit v1.2.3


From 98e527af30a62cfb1e26f2a0ca76289bc7aba4d2 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 6 Nov 2019 18:08:55 -0800
Subject: libbpf: Improve handling of corrupted ELF during map initialization

If we get ELF file with "maps" section, but no symbols pointing to it, we'll
end up with division by zero. Add check against this situation and exit early
with error. Found by Coverity scan against Github libbpf sources.

Fixes: bf82927125dd ("libbpf: refactor map initialization")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191107020855.3834758-6-andriin@fb.com
---
 tools/lib/bpf/libbpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 3ef73a214592..fde6cb3e5d41 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -956,13 +956,13 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	pr_debug("maps in %s: %d maps in %zd bytes\n",
 		 obj->path, nr_maps, data->d_size);
 
-	map_def_sz = data->d_size / nr_maps;
-	if (!data->d_size || (data->d_size % nr_maps) != 0) {
+	if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) {
 		pr_warn("unable to determine map definition size "
 			"section %s, %d maps in %zd bytes\n",
 			obj->path, nr_maps, data->d_size);
 		return -EINVAL;
 	}
+	map_def_sz = data->d_size / nr_maps;
 
 	/* Fill obj->maps using data in "maps" section.  */
 	for (i = 0; i < nr_syms; i++) {
-- 
cgit v1.2.3


From 7e3617a72df32341fea6d226cd6bb21de40c558d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 7 Nov 2019 10:09:03 -0800
Subject: bpf: Add array support to btf_struct_access

This patch adds array support to btf_struct_access().
It supports array of int, array of struct and multidimensional
array.

It also allows using u8[] as a scratch space.  For example,
it allows access the "char cb[48]" with size larger than
the array's element "char".  Another potential use case is
"u64 icsk_ca_priv[]" in the tcp congestion control.

btf_resolve_size() is added to resolve the size of any type.
It will follow the modifier if there is any.  Please
see the function comment for details.

This patch also adds the "off < moff" check at the beginning
of the for loop.  It is to reject cases when "off" is pointing
to a "hole" in a struct.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191107180903.4097702-1-kafai@fb.com
---
 kernel/bpf/btf.c | 195 ++++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 166 insertions(+), 29 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 128d89601d73..4639c4ba9a9b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1036,6 +1036,82 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
 	return env->top_stack ? &env->stack[env->top_stack - 1] : NULL;
 }
 
+/* Resolve the size of a passed-in "type"
+ *
+ * type: is an array (e.g. u32 array[x][y])
+ * return type: type "u32[x][y]", i.e. BTF_KIND_ARRAY,
+ * *type_size: (x * y * sizeof(u32)).  Hence, *type_size always
+ *             corresponds to the return type.
+ * *elem_type: u32
+ * *total_nelems: (x * y).  Hence, individual elem size is
+ *                (*type_size / *total_nelems)
+ *
+ * type: is not an array (e.g. const struct X)
+ * return type: type "struct X"
+ * *type_size: sizeof(struct X)
+ * *elem_type: same as return type ("struct X")
+ * *total_nelems: 1
+ */
+static const struct btf_type *
+btf_resolve_size(const struct btf *btf, const struct btf_type *type,
+		 u32 *type_size, const struct btf_type **elem_type,
+		 u32 *total_nelems)
+{
+	const struct btf_type *array_type = NULL;
+	const struct btf_array *array;
+	u32 i, size, nelems = 1;
+
+	for (i = 0; i < MAX_RESOLVE_DEPTH; i++) {
+		switch (BTF_INFO_KIND(type->info)) {
+		/* type->size can be used */
+		case BTF_KIND_INT:
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+		case BTF_KIND_ENUM:
+			size = type->size;
+			goto resolved;
+
+		case BTF_KIND_PTR:
+			size = sizeof(void *);
+			goto resolved;
+
+		/* Modifiers */
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+			type = btf_type_by_id(btf, type->type);
+			break;
+
+		case BTF_KIND_ARRAY:
+			if (!array_type)
+				array_type = type;
+			array = btf_type_array(type);
+			if (nelems && array->nelems > U32_MAX / nelems)
+				return ERR_PTR(-EINVAL);
+			nelems *= array->nelems;
+			type = btf_type_by_id(btf, array->type);
+			break;
+
+		/* type without size */
+		default:
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+
+resolved:
+	if (nelems && size > U32_MAX / nelems)
+		return ERR_PTR(-EINVAL);
+
+	*type_size = nelems * size;
+	*total_nelems = nelems;
+	*elem_type = type;
+
+	return array_type ? : type;
+}
+
 /* The input param "type_id" must point to a needs_resolve type */
 static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
 						  u32 *type_id)
@@ -3494,10 +3570,10 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id)
 {
+	u32 i, moff, mtrue_end, msize = 0, total_nelems = 0;
+	const struct btf_type *mtype, *elem_type = NULL;
 	const struct btf_member *member;
-	const struct btf_type *mtype;
 	const char *tname, *mname;
-	int i, moff = 0, msize;
 
 again:
 	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
@@ -3507,40 +3583,88 @@ again:
 	}
 
 	for_each_member(i, t, member) {
-		/* offset of the field in bits */
-		moff = btf_member_bit_offset(t, member);
-
 		if (btf_member_bitfield_size(t, member))
 			/* bitfields are not supported yet */
 			continue;
 
-		if (off + size <= moff / 8)
+		/* offset of the field in bytes */
+		moff = btf_member_bit_offset(t, member) / 8;
+		if (off + size <= moff)
 			/* won't find anything, field is already too far */
 			break;
+		/* In case of "off" is pointing to holes of a struct */
+		if (off < moff)
+			continue;
 
 		/* type of the field */
 		mtype = btf_type_by_id(btf_vmlinux, member->type);
 		mname = __btf_name_by_offset(btf_vmlinux, member->name_off);
 
-		/* skip modifiers */
-		while (btf_type_is_modifier(mtype))
-			mtype = btf_type_by_id(btf_vmlinux, mtype->type);
-
-		if (btf_type_is_array(mtype))
-			/* array deref is not supported yet */
-			continue;
-
-		if (!btf_type_has_size(mtype) && !btf_type_is_ptr(mtype)) {
+		mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
+					 &elem_type, &total_nelems);
+		if (IS_ERR(mtype)) {
 			bpf_log(log, "field %s doesn't have size\n", mname);
 			return -EFAULT;
 		}
-		if (btf_type_is_ptr(mtype))
-			msize = 8;
-		else
-			msize = mtype->size;
-		if (off >= moff / 8 + msize)
+
+		mtrue_end = moff + msize;
+		if (off >= mtrue_end)
 			/* no overlap with member, keep iterating */
 			continue;
+
+		if (btf_type_is_array(mtype)) {
+			u32 elem_idx;
+
+			/* btf_resolve_size() above helps to
+			 * linearize a multi-dimensional array.
+			 *
+			 * The logic here is treating an array
+			 * in a struct as the following way:
+			 *
+			 * struct outer {
+			 *	struct inner array[2][2];
+			 * };
+			 *
+			 * looks like:
+			 *
+			 * struct outer {
+			 *	struct inner array_elem0;
+			 *	struct inner array_elem1;
+			 *	struct inner array_elem2;
+			 *	struct inner array_elem3;
+			 * };
+			 *
+			 * When accessing outer->array[1][0], it moves
+			 * moff to "array_elem2", set mtype to
+			 * "struct inner", and msize also becomes
+			 * sizeof(struct inner).  Then most of the
+			 * remaining logic will fall through without
+			 * caring the current member is an array or
+			 * not.
+			 *
+			 * Unlike mtype/msize/moff, mtrue_end does not
+			 * change.  The naming difference ("_true") tells
+			 * that it is not always corresponding to
+			 * the current mtype/msize/moff.
+			 * It is the true end of the current
+			 * member (i.e. array in this case).  That
+			 * will allow an int array to be accessed like
+			 * a scratch space,
+			 * i.e. allow access beyond the size of
+			 *      the array's element as long as it is
+			 *      within the mtrue_end boundary.
+			 */
+
+			/* skip empty array */
+			if (moff == mtrue_end)
+				continue;
+
+			msize /= total_nelems;
+			elem_idx = (off - moff) / msize;
+			moff += elem_idx * msize;
+			mtype = elem_type;
+		}
+
 		/* the 'off' we're looking for is either equal to start
 		 * of this field or inside of this struct
 		 */
@@ -3549,20 +3673,20 @@ again:
 			t = mtype;
 
 			/* adjust offset we're looking for */
-			off -= moff / 8;
+			off -= moff;
 			goto again;
 		}
-		if (msize != size) {
-			/* field access size doesn't match */
-			bpf_log(log,
-				"cannot access %d bytes in struct %s field %s that has size %d\n",
-				size, tname, mname, msize);
-			return -EACCES;
-		}
 
 		if (btf_type_is_ptr(mtype)) {
 			const struct btf_type *stype;
 
+			if (msize != size || off != moff) {
+				bpf_log(log,
+					"cannot access ptr member %s with moff %u in struct %s with off %u size %u\n",
+					mname, moff, tname, off, size);
+				return -EACCES;
+			}
+
 			stype = btf_type_by_id(btf_vmlinux, mtype->type);
 			/* skip modifiers */
 			while (btf_type_is_modifier(stype))
@@ -3572,7 +3696,20 @@ again:
 				return PTR_TO_BTF_ID;
 			}
 		}
-		/* all other fields are treated as scalars */
+
+		/* Allow more flexible access within an int as long as
+		 * it is within mtrue_end.
+		 * Since mtrue_end could be the end of an array,
+		 * that also allows using an array of int as a scratch
+		 * space. e.g. skb->cb[].
+		 */
+		if (off + size > mtrue_end) {
+			bpf_log(log,
+				"access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n",
+				mname, mtrue_end, tname, off, size);
+			return -EACCES;
+		}
+
 		return SCALAR_VALUE;
 	}
 	bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off);
-- 
cgit v1.2.3


From ed5941af3f67ba9062b98aba1a6ca398867dc0de Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 7 Nov 2019 10:09:05 -0800
Subject: bpf: Add cb access in kfree_skb test

Access the skb->cb[] in the kfree_skb test.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191107180905.4097871-1-kafai@fb.com
---
 tools/testing/selftests/bpf/prog_tests/kfree_skb.c | 54 +++++++++++++++++-----
 tools/testing/selftests/bpf/progs/kfree_skb.c      | 25 ++++++++--
 2 files changed, 63 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 430b50de1583..55d36856e621 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -1,15 +1,38 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
+struct meta {
+	int ifindex;
+	__u32 cb32_0;
+	__u8 cb8_0;
+};
+
+static union {
+	__u32 cb32[5];
+	__u8 cb8[20];
+} cb = {
+	.cb32[0] = 0x81828384,
+};
+
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
-	int ifindex = *(int *)data, duration = 0;
-	struct ipv6_packet *pkt_v6 = data + 4;
+	struct meta *meta = (struct meta *)data;
+	struct ipv6_packet *pkt_v6 = data + sizeof(*meta);
+	int duration = 0;
 
-	if (ifindex != 1)
+	if (CHECK(size != 72 + sizeof(*meta), "check_size", "size %u != %zu\n",
+		  size, 72 + sizeof(*meta)))
+		return;
+	if (CHECK(meta->ifindex != 1, "check_meta_ifindex",
+		  "meta->ifindex = %d\n", meta->ifindex))
 		/* spurious kfree_skb not on loopback device */
 		return;
-	if (CHECK(size != 76, "check_size", "size %u != 76\n", size))
+	if (CHECK(meta->cb8_0 != cb.cb8[0], "check_cb8_0", "cb8_0 %x != %x\n",
+		  meta->cb8_0, cb.cb8[0]))
+		return;
+	if (CHECK(meta->cb32_0 != cb.cb32[0], "check_cb32_0",
+		  "cb32_0 %x != %x\n",
+		  meta->cb32_0, cb.cb32[0]))
 		return;
 	if (CHECK(pkt_v6->eth.h_proto != 0xdd86, "check_eth",
 		  "h_proto %x\n", pkt_v6->eth.h_proto))
@@ -26,6 +49,13 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 
 void test_kfree_skb(void)
 {
+	struct __sk_buff skb = {};
+	struct bpf_prog_test_run_attr tattr = {
+		.data_in = &pkt_v6,
+		.data_size_in = sizeof(pkt_v6),
+		.ctx_in = &skb,
+		.ctx_size_in = sizeof(skb),
+	};
 	struct bpf_prog_load_attr attr = {
 		.file = "./kfree_skb.o",
 	};
@@ -36,11 +66,12 @@ void test_kfree_skb(void)
 	struct bpf_link *link = NULL;
 	struct bpf_map *perf_buf_map;
 	struct bpf_program *prog;
-	__u32 duration, retval;
-	int err, pkt_fd, kfree_skb_fd;
+	int err, kfree_skb_fd;
 	bool passed = false;
+	__u32 duration = 0;
 
-	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &pkt_fd);
+	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &obj, &tattr.prog_fd);
 	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
 		return;
 
@@ -66,11 +97,12 @@ void test_kfree_skb(void)
 	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
 		goto close_prog;
 
-	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
-				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "ipv6",
+	memcpy(skb.cb, &cb, sizeof(cb));
+	err = bpf_prog_test_run_xattr(&tattr);
+	duration = tattr.duration;
+	CHECK(err || tattr.retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
-	      err, errno, retval, duration);
+	      err, errno, tattr.retval, duration);
 
 	/* read perf buffer */
 	err = perf_buffer__poll(pb, 100);
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 489319ea1d6a..f769fdbf6725 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -43,6 +43,7 @@ struct sk_buff {
 	refcount_t users;
 	unsigned char *data;
 	char __pkt_type_offset[0];
+	char cb[48];
 };
 
 /* copy arguments from
@@ -57,28 +58,41 @@ struct trace_kfree_skb {
 	void *location;
 };
 
+struct meta {
+	int ifindex;
+	__u32 cb32_0;
+	__u8 cb8_0;
+};
+
 SEC("tp_btf/kfree_skb")
 int trace_kfree_skb(struct trace_kfree_skb *ctx)
 {
 	struct sk_buff *skb = ctx->skb;
 	struct net_device *dev;
-	int ifindex;
 	struct callback_head *ptr;
 	void *func;
 	int users;
 	unsigned char *data;
 	unsigned short pkt_data;
+	struct meta meta = {};
 	char pkt_type;
+	__u32 *cb32;
+	__u8 *cb8;
 
 	__builtin_preserve_access_index(({
 		users = skb->users.refs.counter;
 		data = skb->data;
 		dev = skb->dev;
-		ifindex = dev->ifindex;
 		ptr = dev->ifalias->rcuhead.next;
 		func = ptr->func;
+		cb8 = (__u8 *)&skb->cb;
+		cb32 = (__u32 *)&skb->cb;
 	}));
 
+	meta.ifindex = _(dev->ifindex);
+	meta.cb8_0 = cb8[8];
+	meta.cb32_0 = cb32[2];
+
 	bpf_probe_read_kernel(&pkt_type, sizeof(pkt_type), _(&skb->__pkt_type_offset));
 	pkt_type &= 7;
 
@@ -90,14 +104,15 @@ int trace_kfree_skb(struct trace_kfree_skb *ctx)
 		   _(skb->len), users, pkt_type);
 	bpf_printk("skb->queue_mapping %d\n", _(skb->queue_mapping));
 	bpf_printk("dev->ifindex %d data %llx pkt_data %x\n",
-		   ifindex, data, pkt_data);
+		   meta.ifindex, data, pkt_data);
+	bpf_printk("cb8_0:%x cb32_0:%x\n", meta.cb8_0, meta.cb32_0);
 
-	if (users != 1 || pkt_data != bpf_htons(0x86dd) || ifindex != 1)
+	if (users != 1 || pkt_data != bpf_htons(0x86dd) || meta.ifindex != 1)
 		/* raw tp ignores return value */
 		return 0;
 
 	/* send first 72 byte of the packet to user space */
 	bpf_skb_output(skb, &perf_buf_map, (72ull << 32) | BPF_F_CURRENT_CPU,
-		       &ifindex, sizeof(ifindex));
+		       &meta, sizeof(meta));
 	return 0;
 }
-- 
cgit v1.2.3


From afbe3c27d9ae151be33ccd6b05699d3c49dabad2 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Thu, 7 Nov 2019 09:51:52 +0900
Subject: samples: bpf: Update outdated error message

Currently, under samples, several methods are being used to load bpf
program.

Since using libbpf is preferred solution, lots of previously used
'load_bpf_file' from bpf_load are replaced with 'bpf_prog_load_xattr'
from libbpf.

But some of the error messages still show up as 'load_bpf_file' instead
of 'bpf_prog_load_xattr'.

This commit fixes outdated errror messages under samples and fixes some
code style issues.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191107005153.31541-2-danieltimlee@gmail.com
---
 samples/bpf/hbm.c                  | 2 +-
 samples/bpf/xdp1_user.c            | 2 +-
 samples/bpf/xdp_rxq_info_user.c    | 6 +++---
 samples/bpf/xdp_sample_pkts_user.c | 2 +-
 samples/bpf/xdp_tx_iptunnel_user.c | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index e0fbab9bec83..829b68d87687 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -147,7 +147,7 @@ static int prog_load(char *prog)
 	}
 
 	if (ret) {
-		printf("ERROR: load_bpf_file failed for: %s\n", prog);
+		printf("ERROR: bpf_prog_load_xattr failed for: %s\n", prog);
 		printf("  Output from verifier:\n%s\n------\n", bpf_log_buf);
 		ret = -1;
 	} else {
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index a8e5fa02e8a8..3e553eed95a7 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -139,7 +139,7 @@ int main(int argc, char **argv)
 	map_fd = bpf_map__fd(map);
 
 	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
 		return 1;
 	}
 
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index c7e4e45d824a..51e0d810e070 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -51,8 +51,8 @@ static const struct option long_options[] = {
 	{"sec",		required_argument,	NULL, 's' },
 	{"no-separators", no_argument,		NULL, 'z' },
 	{"action",	required_argument,	NULL, 'a' },
-	{"readmem", 	no_argument,		NULL, 'r' },
-	{"swapmac", 	no_argument,		NULL, 'm' },
+	{"readmem",	no_argument,		NULL, 'r' },
+	{"swapmac",	no_argument,		NULL, 'm' },
 	{"force",	no_argument,		NULL, 'F' },
 	{0, 0, NULL,  0 }
 };
@@ -499,7 +499,7 @@ int main(int argc, char **argv)
 	map_fd = bpf_map__fd(map);
 
 	if (!prog_fd) {
-		fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
+		fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", strerror(errno));
 		return EXIT_FAIL;
 	}
 
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index 3002714e3cd5..a5760e8bf2c4 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -150,7 +150,7 @@ int main(int argc, char **argv)
 		return 1;
 
 	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
 		return 1;
 	}
 
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index dfb68582e243..2fe4c7f5ffe5 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -268,7 +268,7 @@ int main(int argc, char **argv)
 		return 1;
 
 	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
 		return 1;
 	}
 
-- 
cgit v1.2.3


From 451d1dc886b548d6e18c933adca326c1307023c9 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Thu, 7 Nov 2019 09:51:53 +0900
Subject: samples: bpf: update map definition to new syntax BTF-defined map

Since, the new syntax of BTF-defined map has been introduced,
the syntax for using maps under samples directory are mixed up.
For example, some are already using the new syntax, and some are using
existing syntax by calling them as 'legacy'.

As stated at commit abd29c931459 ("libbpf: allow specifying map
definitions using BTF"), the BTF-defined map has more compatablility
with extending supported map definition features.

The commit doesn't replace all of the map to new BTF-defined map,
because some of the samples still use bpf_load instead of libbpf, which
can't properly create BTF-defined map.

This will only updates the samples which uses libbpf API for loading bpf
program. (ex. bpf_prog_load_xattr)

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/sockex1_kern.c          |  12 ++--
 samples/bpf/sockex2_kern.c          |  12 ++--
 samples/bpf/xdp1_kern.c             |  12 ++--
 samples/bpf/xdp2_kern.c             |  12 ++--
 samples/bpf/xdp_adjust_tail_kern.c  |  12 ++--
 samples/bpf/xdp_fwd_kern.c          |  13 ++---
 samples/bpf/xdp_redirect_cpu_kern.c | 108 ++++++++++++++++++------------------
 samples/bpf/xdp_redirect_kern.c     |  24 ++++----
 samples/bpf/xdp_redirect_map_kern.c |  24 ++++----
 samples/bpf/xdp_router_ipv4_kern.c  |  64 ++++++++++-----------
 samples/bpf/xdp_rxq_info_kern.c     |  37 ++++++------
 samples/bpf/xdp_tx_iptunnel_kern.c  |  26 ++++-----
 12 files changed, 178 insertions(+), 178 deletions(-)

diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
index f96943f443ab..2408dbfb7a21 100644
--- a/samples/bpf/sockex1_kern.c
+++ b/samples/bpf/sockex1_kern.c
@@ -5,12 +5,12 @@
 #include "bpf_helpers.h"
 #include "bpf_legacy.h"
 
-struct bpf_map_def SEC("maps") my_map = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} my_map SEC(".maps");
 
 SEC("socket1")
 int bpf_prog1(struct __sk_buff *skb)
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index 5566fa7d92fa..a7bcd03bf529 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -190,12 +190,12 @@ struct pair {
 	long bytes;
 };
 
-struct bpf_map_def SEC("maps") hash_map = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__be32),
-	.value_size = sizeof(struct pair),
-	.max_entries = 1024,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, struct pair);
+	__uint(max_entries, 1024);
+} hash_map SEC(".maps");
 
 SEC("socket2")
 int bpf_prog2(struct __sk_buff *skb)
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
index 219742106bfd..db6870aee42c 100644
--- a/samples/bpf/xdp1_kern.c
+++ b/samples/bpf/xdp1_kern.c
@@ -14,12 +14,12 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
 
 static int parse_ipv4(void *data, u64 nh_off, void *data_end)
 {
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
index e01288867d15..c74b52c6d945 100644
--- a/samples/bpf/xdp2_kern.c
+++ b/samples/bpf/xdp2_kern.c
@@ -14,12 +14,12 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
 
 static void swap_src_dst_mac(void *data)
 {
diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
index c616508befb9..0f707e0fb375 100644
--- a/samples/bpf/xdp_adjust_tail_kern.c
+++ b/samples/bpf/xdp_adjust_tail_kern.c
@@ -28,12 +28,12 @@
 /* volatile to prevent compiler optimizations */
 static volatile __u32 max_pcktsz = MAX_PCKT_SIZE;
 
-struct bpf_map_def SEC("maps") icmpcnt = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 1);
+} icmpcnt SEC(".maps");
 
 static __always_inline void count_icmp(void)
 {
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index 701a30f258b1..d013029aeaa2 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -23,13 +23,12 @@
 
 #define IPV6_FLOWINFO_MASK              cpu_to_be32(0x0FFFFFFF)
 
-/* For TX-traffic redirect requires net_device ifindex to be in this devmap */
-struct bpf_map_def SEC("maps") xdp_tx_ports = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 64,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 64);
+} xdp_tx_ports SEC(".maps");
 
 /* from include/net/ip.h */
 static __always_inline int ip_decrease_ttl(struct iphdr *iph)
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index a306d1c75622..cfcc31e51197 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -18,12 +18,12 @@
 #define MAX_CPUS 64 /* WARNING - sync with _user.c */
 
 /* Special map type that can XDP_REDIRECT frames to another CPU */
-struct bpf_map_def SEC("maps") cpu_map = {
-	.type		= BPF_MAP_TYPE_CPUMAP,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= MAX_CPUS,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u32));
+	__uint(max_entries, MAX_CPUS);
+} cpu_map SEC(".maps");
 
 /* Common stats data record to keep userspace more simple */
 struct datarec {
@@ -35,67 +35,67 @@ struct datarec {
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
  */
-struct bpf_map_def SEC("maps") rx_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} rx_cnt SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") redirect_err_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 2,
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 2);
 	/* TODO: have entries for all possible errno's */
-};
+} redirect_err_cnt SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= MAX_CPUS,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, MAX_CPUS);
+} cpumap_enqueue_cnt SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") cpumap_kthread_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} cpumap_kthread_cnt SEC(".maps");
 
 /* Set of maps controlling available CPU, and for iterating through
  * selectable redirect CPUs.
  */
-struct bpf_map_def SEC("maps") cpus_available = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= MAX_CPUS,
-};
-struct bpf_map_def SEC("maps") cpus_count = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= 1,
-};
-struct bpf_map_def SEC("maps") cpus_iterator = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, MAX_CPUS);
+} cpus_available SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 1);
+} cpus_count SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 1);
+} cpus_iterator SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") exception_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} exception_cnt SEC(".maps");
 
 /* Helper parse functions */
 
diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c
index 8abb151e385f..1f0b7d05abb2 100644
--- a/samples/bpf/xdp_redirect_kern.c
+++ b/samples/bpf/xdp_redirect_kern.c
@@ -19,22 +19,22 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+} tx_port SEC(".maps");
 
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
  */
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 1);
+} rxcnt SEC(".maps");
 
 static void swap_src_dst_mac(void *data)
 {
diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c
index 740a529ba84f..4631b484c432 100644
--- a/samples/bpf/xdp_redirect_map_kern.c
+++ b/samples/bpf/xdp_redirect_map_kern.c
@@ -19,22 +19,22 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 100,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 100);
+} tx_port SEC(".maps");
 
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
  */
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 1);
+} rxcnt SEC(".maps");
 
 static void swap_src_dst_mac(void *data)
 {
diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c
index 993f56bc7b9a..bf11efc8e949 100644
--- a/samples/bpf/xdp_router_ipv4_kern.c
+++ b/samples/bpf/xdp_router_ipv4_kern.c
@@ -42,44 +42,44 @@ struct direct_map {
 };
 
 /* Map for trie implementation*/
-struct bpf_map_def SEC("maps") lpm_map = {
-	.type = BPF_MAP_TYPE_LPM_TRIE,
-	.key_size = 8,
-	.value_size = sizeof(struct trie_value),
-	.max_entries = 50,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__uint(key_size, 8);
+	__uint(value_size, sizeof(struct trie_value));
+	__uint(max_entries, 50);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} lpm_map SEC(".maps");
 
 /* Map for counter*/
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(u64),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, u64);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
 
 /* Map for ARP table*/
-struct bpf_map_def SEC("maps") arp_table = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__be32),
-	.value_size = sizeof(__be64),
-	.max_entries = 50,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, __be64);
+	__uint(max_entries, 50);
+} arp_table SEC(".maps");
 
 /* Map to keep the exact match entries in the route table*/
-struct bpf_map_def SEC("maps") exact_match = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__be32),
-	.value_size = sizeof(struct direct_map),
-	.max_entries = 50,
-};
-
-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 100,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, struct direct_map);
+	__uint(max_entries, 50);
+} exact_match SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 100);
+} tx_port SEC(".maps");
 
 /* Function to set source and destination mac of the packet */
 static inline void set_src_dst_mac(void *data, void *src, void *dst)
diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
index 222a83eed1cb..272d0f82a6b5 100644
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ b/samples/bpf/xdp_rxq_info_kern.c
@@ -23,12 +23,13 @@ enum cfg_options_flags {
 	READ_MEM = 0x1U,
 	SWAP_MAC = 0x2U,
 };
-struct bpf_map_def SEC("maps") config_map = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(int),
-	.value_size	= sizeof(struct config),
-	.max_entries	= 1,
-};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct config);
+	__uint(max_entries, 1);
+} config_map SEC(".maps");
 
 /* Common stats data record (shared with userspace) */
 struct datarec {
@@ -36,22 +37,22 @@ struct datarec {
 	__u64 issue;
 };
 
-struct bpf_map_def SEC("maps") stats_global_map = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} stats_global_map SEC(".maps");
 
 #define MAX_RXQs 64
 
 /* Stats per rx_queue_index (per CPU) */
-struct bpf_map_def SEC("maps") rx_queue_index_map = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= MAX_RXQs + 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, MAX_RXQs + 1);
+} rx_queue_index_map SEC(".maps");
 
 static __always_inline
 void swap_src_dst_mac(void *data)
diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c
index 0f4f6e8c8611..6db450a5c1ca 100644
--- a/samples/bpf/xdp_tx_iptunnel_kern.c
+++ b/samples/bpf/xdp_tx_iptunnel_kern.c
@@ -19,19 +19,19 @@
 #include "bpf_helpers.h"
 #include "xdp_tx_iptunnel_common.h"
 
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 256,
-};
-
-struct bpf_map_def SEC("maps") vip2tnl = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip),
-	.value_size = sizeof(struct iptnl_info),
-	.max_entries = MAX_IPTNL_ENTRIES,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct vip);
+	__type(value, struct iptnl_info);
+	__uint(max_entries, MAX_IPTNL_ENTRIES);
+} vip2tnl SEC(".maps");
 
 static __always_inline void count_tx(u32 protocol)
 {
-- 
cgit v1.2.3


From ec6d5f47bfe36f46aa0de707e5beb2f58d96b76d Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Sat, 9 Nov 2019 21:37:27 +0100
Subject: libbpf: Unpin auto-pinned maps if loading fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the automatic map-pinning happens during load, it will leave pinned
maps around if the load fails at a later stage. Fix this by unpinning any
pinned maps on cleanup. To avoid unpinning pinned maps that were reused
rather than newly pinned, add a new boolean property on struct bpf_map to
keep track of whether that map was reused or not; and only unpin those maps
that were not reused.

Fixes: 57a00f41644f ("libbpf: Add auto-pinning of maps when loading BPF objects")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/157333184731.88376.9992935027056165873.stgit@toke.dk
---
 tools/lib/bpf/libbpf.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fde6cb3e5d41..d8ead85903d1 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -229,6 +229,7 @@ struct bpf_map {
 	enum libbpf_map_type libbpf_type;
 	char *pin_path;
 	bool pinned;
+	bool reused;
 };
 
 struct bpf_secdata {
@@ -1995,6 +1996,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	map->def.map_flags = info.map_flags;
 	map->btf_key_type_id = info.btf_key_type_id;
 	map->btf_value_type_id = info.btf_value_type_id;
+	map->reused = true;
 
 	return 0;
 
@@ -4026,7 +4028,7 @@ int bpf_object__unload(struct bpf_object *obj)
 int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 {
 	struct bpf_object *obj;
-	int err;
+	int err, i;
 
 	if (!attr)
 		return -EINVAL;
@@ -4047,6 +4049,11 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 
 	return 0;
 out:
+	/* unpin any maps that were auto-pinned during load */
+	for (i = 0; i < obj->nr_maps; i++)
+		if (obj->maps[i].pinned && !obj->maps[i].reused)
+			bpf_map__unpin(&obj->maps[i], NULL);
+
 	bpf_object__unload(obj);
 	pr_warn("failed to load object '%s'\n", obj->path);
 	return err;
-- 
cgit v1.2.3


From 9c4e395a1e8c1dc14189b88f24d111f80353b9a4 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Sat, 9 Nov 2019 21:37:28 +0100
Subject: selftests/bpf: Add tests for automatic map unpinning on load failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This add tests for the different variations of automatic map unpinning on
load failure.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/157333184838.88376.8243704248624814775.stgit@toke.dk
---
 tools/testing/selftests/bpf/prog_tests/pinning.c | 20 +++++++++++++++++---
 tools/testing/selftests/bpf/progs/test_pinning.c |  2 +-
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c
index 525388971e08..041952524c55 100644
--- a/tools/testing/selftests/bpf/prog_tests/pinning.c
+++ b/tools/testing/selftests/bpf/prog_tests/pinning.c
@@ -163,12 +163,15 @@ void test_pinning(void)
 		goto out;
 	}
 
-	/* swap pin paths of the two maps */
+	/* set pin paths so that nopinmap2 will attempt to reuse the map at
+	 * pinpath (which will fail), but not before pinmap has already been
+	 * reused
+	 */
 	bpf_object__for_each_map(map, obj) {
 		if (!strcmp(bpf_map__name(map), "nopinmap"))
+			err = bpf_map__set_pin_path(map, nopinpath2);
+		else if (!strcmp(bpf_map__name(map), "nopinmap2"))
 			err = bpf_map__set_pin_path(map, pinpath);
-		else if (!strcmp(bpf_map__name(map), "pinmap"))
-			err = bpf_map__set_pin_path(map, NULL);
 		else
 			continue;
 
@@ -181,6 +184,17 @@ void test_pinning(void)
 	if (CHECK(err != -EINVAL, "param mismatch load", "err %d errno %d\n", err, errno))
 		goto out;
 
+	/* nopinmap2 should have been pinned and cleaned up again */
+	err = stat(nopinpath2, &statbuf);
+	if (CHECK(!err || errno != ENOENT, "stat nopinpath2",
+		  "err %d errno %d\n", err, errno))
+		goto out;
+
+	/* pinmap should still be there */
+	err = stat(pinpath, &statbuf);
+	if (CHECK(err, "stat pinpath", "err %d errno %d\n", err, errno))
+		goto out;
+
 	bpf_object__close(obj);
 
 	/* test auto-pinning at custom path with open opt */
diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c
index f69a4a50d056..f20e7e00373f 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning.c
@@ -21,7 +21,7 @@ struct {
 } nopinmap SEC(".maps");
 
 struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(type, BPF_MAP_TYPE_HASH);
 	__uint(max_entries, 1);
 	__type(key, __u32);
 	__type(value, __u64);
-- 
cgit v1.2.3


From 4f33ddb4e3e28ade924fbf05ec8bcd7d5c022fee Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Sat, 9 Nov 2019 21:37:29 +0100
Subject: libbpf: Propagate EPERM to caller on program load
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When loading an eBPF program, libbpf overrides the return code for EPERM
errors instead of returning it to the caller. This makes it hard to figure
out what went wrong on load.

In particular, EPERM is returned when the system rlimit is too low to lock
the memory required for the BPF program. Previously, this was somewhat
obscured because the rlimit error would be hit on map creation (which does
return it correctly). However, since maps can now be reused, object load
can proceed all the way to loading programs without hitting the error;
propagating it even in this case makes it possible for the caller to react
appropriately (and, e.g., attempt to raise the rlimit before retrying).

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/157333184946.88376.11768171652794234561.stgit@toke.dk
---
 tools/lib/bpf/libbpf.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d8ead85903d1..847b62895f9b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3721,7 +3721,7 @@ retry_load:
 		free(log_buf);
 		goto retry_load;
 	}
-	ret = -LIBBPF_ERRNO__LOAD;
+	ret = -errno;
 	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 	pr_warn("load bpf program failed: %s\n", cp);
 
@@ -3734,23 +3734,18 @@ retry_load:
 		pr_warn("Program too large (%zu insns), at most %d insns\n",
 			load_attr.insns_cnt, BPF_MAXINSNS);
 		ret = -LIBBPF_ERRNO__PROG2BIG;
-	} else {
+	} else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
 		/* Wrong program type? */
-		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
-			int fd;
-
-			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
-			load_attr.expected_attach_type = 0;
-			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
-			if (fd >= 0) {
-				close(fd);
-				ret = -LIBBPF_ERRNO__PROGTYPE;
-				goto out;
-			}
-		}
+		int fd;
 
-		if (log_buf)
-			ret = -LIBBPF_ERRNO__KVER;
+		load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
+		load_attr.expected_attach_type = 0;
+		fd = bpf_load_program_xattr(&load_attr, NULL, 0);
+		if (fd >= 0) {
+			close(fd);
+			ret = -LIBBPF_ERRNO__PROGTYPE;
+			goto out;
+		}
 	}
 
 out:
-- 
cgit v1.2.3


From b6e99b010ecf829fd8453a7a77e389501bb81990 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Sat, 9 Nov 2019 21:37:30 +0100
Subject: libbpf: Use pr_warn() when printing netlink errors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The netlink functions were using fprintf(stderr, ) directly to print out
error messages, instead of going through the usual logging macros. This
makes it impossible for the calling application to silence or redirect
those error messages. Fix this by switching to pr_warn() in nlattr.c and
netlink.c.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/157333185055.88376.15999360127117901443.stgit@toke.dk
---
 tools/lib/bpf/netlink.c |  3 ++-
 tools/lib/bpf/nlattr.c  | 10 +++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index ce3ec81b71c0..a261df9cb488 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -12,6 +12,7 @@
 
 #include "bpf.h"
 #include "libbpf.h"
+#include "libbpf_internal.h"
 #include "nlattr.h"
 
 #ifndef SOL_NETLINK
@@ -43,7 +44,7 @@ int libbpf_netlink_open(__u32 *nl_pid)
 
 	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
 		       &one, sizeof(one)) < 0) {
-		fprintf(stderr, "Netlink error reporting not supported\n");
+		pr_warn("Netlink error reporting not supported\n");
 	}
 
 	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 1e69c0c8d413..8db44bbfc66d 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -8,6 +8,7 @@
 
 #include <errno.h>
 #include "nlattr.h"
+#include "libbpf_internal.h"
 #include <linux/rtnetlink.h>
 #include <string.h>
 #include <stdio.h>
@@ -121,8 +122,8 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
 		}
 
 		if (tb[type])
-			fprintf(stderr, "Attribute of type %#x found multiple times in message, "
-				  "previous attribute is being ignored.\n", type);
+			pr_warn("Attribute of type %#x found multiple times in message, "
+				"previous attribute is being ignored.\n", type);
 
 		tb[type] = nla;
 	}
@@ -181,15 +182,14 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
 
 	if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
 			     extack_policy) != 0) {
-		fprintf(stderr,
-			"Failed to parse extended error attributes\n");
+		pr_warn("Failed to parse extended error attributes\n");
 		return 0;
 	}
 
 	if (tb[NLMSGERR_ATTR_MSG])
 		errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
 
-	fprintf(stderr, "Kernel error message: %s\n", errmsg);
+	pr_warn("Kernel error message: %s\n", errmsg);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 473f4e133a12dd083bae044ba1782be4767177c1 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Sat, 9 Nov 2019 21:37:31 +0100
Subject: libbpf: Add bpf_get_link_xdp_info() function to get more XDP
 information
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, libbpf only provides a function to get a single ID for the XDP
program attached to the interface. However, it can be useful to get the
full set of program IDs attached, along with the attachment mode, in one
go. Add a new getter function to support this, using an extendible
structure to carry the information. Express the old bpf_get_link_id()
function in terms of the new function.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/157333185164.88376.7520653040667637246.stgit@toke.dk
---
 tools/lib/bpf/libbpf.h   | 10 ++++++
 tools/lib/bpf/libbpf.map |  1 +
 tools/lib/bpf/netlink.c  | 84 ++++++++++++++++++++++++++++++++----------------
 3 files changed, 67 insertions(+), 28 deletions(-)

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6ddc0419337b..f0947cc949d2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -427,8 +427,18 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
 			     struct bpf_object **pobj, int *prog_fd);
 
+struct xdp_link_info {
+	__u32 prog_id;
+	__u32 drv_prog_id;
+	__u32 hw_prog_id;
+	__u32 skb_prog_id;
+	__u8 attach_mode;
+};
+
 LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+				     size_t info_size, __u32 flags);
 
 struct perf_buffer;
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 86173cbb159d..d1a782a3a58d 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -193,6 +193,7 @@ LIBBPF_0.0.5 {
 
 LIBBPF_0.0.6 {
 	global:
+		bpf_get_link_xdp_info;
 		bpf_map__get_pin_path;
 		bpf_map__is_pinned;
 		bpf_map__set_pin_path;
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index a261df9cb488..5065c1aa1061 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -25,7 +25,7 @@ typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
 struct xdp_id_md {
 	int ifindex;
 	__u32 flags;
-	__u32 id;
+	struct xdp_link_info info;
 };
 
 int libbpf_netlink_open(__u32 *nl_pid)
@@ -203,26 +203,11 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 	return dump_link_nlmsg(cookie, ifi, tb);
 }
 
-static unsigned char get_xdp_id_attr(unsigned char mode, __u32 flags)
-{
-	if (mode != XDP_ATTACHED_MULTI)
-		return IFLA_XDP_PROG_ID;
-	if (flags & XDP_FLAGS_DRV_MODE)
-		return IFLA_XDP_DRV_PROG_ID;
-	if (flags & XDP_FLAGS_HW_MODE)
-		return IFLA_XDP_HW_PROG_ID;
-	if (flags & XDP_FLAGS_SKB_MODE)
-		return IFLA_XDP_SKB_PROG_ID;
-
-	return IFLA_XDP_UNSPEC;
-}
-
-static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
+static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct nlattr *xdp_tb[IFLA_XDP_MAX + 1];
 	struct xdp_id_md *xdp_id = cookie;
 	struct ifinfomsg *ifinfo = msg;
-	unsigned char mode, xdp_attr;
 	int ret;
 
 	if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index)
@@ -238,27 +223,40 @@ static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
 	if (!xdp_tb[IFLA_XDP_ATTACHED])
 		return 0;
 
-	mode = libbpf_nla_getattr_u8(xdp_tb[IFLA_XDP_ATTACHED]);
-	if (mode == XDP_ATTACHED_NONE)
-		return 0;
+	xdp_id->info.attach_mode = libbpf_nla_getattr_u8(
+		xdp_tb[IFLA_XDP_ATTACHED]);
 
-	xdp_attr = get_xdp_id_attr(mode, xdp_id->flags);
-	if (!xdp_attr || !xdp_tb[xdp_attr])
+	if (xdp_id->info.attach_mode == XDP_ATTACHED_NONE)
 		return 0;
 
-	xdp_id->id = libbpf_nla_getattr_u32(xdp_tb[xdp_attr]);
+	if (xdp_tb[IFLA_XDP_PROG_ID])
+		xdp_id->info.prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_SKB_PROG_ID])
+		xdp_id->info.skb_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_SKB_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_DRV_PROG_ID])
+		xdp_id->info.drv_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_DRV_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_HW_PROG_ID])
+		xdp_id->info.hw_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_HW_PROG_ID]);
 
 	return 0;
 }
 
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+			  size_t info_size, __u32 flags)
 {
 	struct xdp_id_md xdp_id = {};
 	int sock, ret;
 	__u32 nl_pid;
 	__u32 mask;
 
-	if (flags & ~XDP_FLAGS_MASK)
+	if (flags & ~XDP_FLAGS_MASK || !info_size)
 		return -EINVAL;
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
@@ -274,14 +272,44 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
 	xdp_id.ifindex = ifindex;
 	xdp_id.flags = flags;
 
-	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_id, &xdp_id);
-	if (!ret)
-		*prog_id = xdp_id.id;
+	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id);
+	if (!ret) {
+		size_t sz = min(info_size, sizeof(xdp_id.info));
+
+		memcpy(info, &xdp_id.info, sz);
+		memset((void *) info + sz, 0, info_size - sz);
+	}
 
 	close(sock);
 	return ret;
 }
 
+static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
+{
+	if (info->attach_mode != XDP_ATTACHED_MULTI)
+		return info->prog_id;
+	if (flags & XDP_FLAGS_DRV_MODE)
+		return info->drv_prog_id;
+	if (flags & XDP_FLAGS_HW_MODE)
+		return info->hw_prog_id;
+	if (flags & XDP_FLAGS_SKB_MODE)
+		return info->skb_prog_id;
+
+	return 0;
+}
+
+int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+{
+	struct xdp_link_info info;
+	int ret;
+
+	ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags);
+	if (!ret)
+		*prog_id = get_xdp_id(&info, flags);
+
+	return ret;
+}
+
 int libbpf_nl_get_link(int sock, unsigned int nl_pid,
 		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
-- 
cgit v1.2.3


From 1a734efe06948c17122808f74f0c8cc550c10cf5 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Sat, 9 Nov 2019 21:37:32 +0100
Subject: libbpf: Add getter for program size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds a new getter for the BPF program size (in bytes). This is useful
for a caller that is trying to predict how much memory will be locked by
loading a BPF object into the kernel.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/157333185272.88376.10996937115395724683.stgit@toke.dk
---
 tools/lib/bpf/libbpf.c   | 5 +++++
 tools/lib/bpf/libbpf.h   | 3 +++
 tools/lib/bpf/libbpf.map | 1 +
 3 files changed, 9 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 847b62895f9b..96ef18cfeffb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4782,6 +4782,11 @@ int bpf_program__fd(const struct bpf_program *prog)
 	return bpf_program__nth_fd(prog, 0);
 }
 
+size_t bpf_program__size(const struct bpf_program *prog)
+{
+	return prog->insns_cnt * sizeof(struct bpf_insn);
+}
+
 int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
 			  bpf_program_prep_t prep)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f0947cc949d2..5aa27caad6c2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -214,6 +214,9 @@ LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
 LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog,
 					  bool needs_copy);
 
+/* returns program size in bytes */
+LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog);
+
 LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
 				 __u32 kern_version);
 LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index d1a782a3a58d..9f39ee06b2d4 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -203,4 +203,5 @@ LIBBPF_0.0.6 {
 		bpf_program__get_type;
 		bpf_program__is_tracing;
 		bpf_program__set_tracing;
+		bpf_program__size;
 } LIBBPF_0.0.5;
-- 
cgit v1.2.3


From cbf07409d0c2afad7bb54be039490bffad8bc737 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 7 Nov 2019 18:47:36 +0100
Subject: libbpf: Support XDP_SHARED_UMEM with external XDP program

Add support in libbpf to create multiple sockets that share a single
umem. Note that an external XDP program need to be supplied that
routes the incoming traffic to the desired sockets. So you need to
supply the libbpf_flag XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD and load
your own XDP program.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: William Tu <u9012063@gmail.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/1573148860-30254-2-git-send-email-magnus.karlsson@intel.com
---
 tools/lib/bpf/xsk.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 86c1b61017f6..8ebd810931ab 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -586,15 +586,21 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	if (!umem || !xsk_ptr || !rx || !tx)
 		return -EFAULT;
 
-	if (umem->refcount) {
-		pr_warn("Error: shared umems not supported by libbpf.\n");
-		return -EBUSY;
-	}
-
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
 		return -ENOMEM;
 
+	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	if (err)
+		goto out_xsk_alloc;
+
+	if (umem->refcount &&
+	    !(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
+		pr_warn("Error: shared umems not supported by libbpf supplied XDP program.\n");
+		err = -EBUSY;
+		goto out_xsk_alloc;
+	}
+
 	if (umem->refcount++ > 0) {
 		xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
 		if (xsk->fd < 0) {
@@ -616,10 +622,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	memcpy(xsk->ifname, ifname, IFNAMSIZ - 1);
 	xsk->ifname[IFNAMSIZ - 1] = '\0';
 
-	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
-	if (err)
-		goto out_socket;
-
 	if (rx) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
 				 &xsk->config.rx_size,
@@ -687,7 +689,12 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	sxdp.sxdp_family = PF_XDP;
 	sxdp.sxdp_ifindex = xsk->ifindex;
 	sxdp.sxdp_queue_id = xsk->queue_id;
-	sxdp.sxdp_flags = xsk->config.bind_flags;
+	if (umem->refcount > 1) {
+		sxdp.sxdp_flags = XDP_SHARED_UMEM;
+		sxdp.sxdp_shared_umem_fd = umem->fd;
+	} else {
+		sxdp.sxdp_flags = xsk->config.bind_flags;
+	}
 
 	err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp));
 	if (err) {
-- 
cgit v1.2.3


From 2e5d72c15f0dc713c203464c5c76eb4ec285f598 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 7 Nov 2019 18:47:37 +0100
Subject: samples/bpf: Add XDP_SHARED_UMEM support to xdpsock

Add support for the XDP_SHARED_UMEM mode to the xdpsock sample
application. As libbpf does not have a built in XDP program for this
mode, we use an explicitly loaded XDP program. This also serves as an
example on how to write your own XDP program that can route to an
AF_XDP socket.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: William Tu <u9012063@gmail.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/1573148860-30254-3-git-send-email-magnus.karlsson@intel.com
---
 samples/bpf/Makefile       |   1 +
 samples/bpf/xdpsock.h      |  11 ++++
 samples/bpf/xdpsock_kern.c |  24 ++++++++
 samples/bpf/xdpsock_user.c | 141 +++++++++++++++++++++++++++++++--------------
 4 files changed, 135 insertions(+), 42 deletions(-)
 create mode 100644 samples/bpf/xdpsock.h
 create mode 100644 samples/bpf/xdpsock_kern.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4df11ddb9c75..8a9af3ab7769 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -167,6 +167,7 @@ always += xdp_sample_pkts_kern.o
 always += ibumad_kern.o
 always += hbm_out_kern.o
 always += hbm_edt_kern.o
+always += xdpsock_kern.o
 
 ifeq ($(ARCH), arm)
 # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h
new file mode 100644
index 000000000000..b7eca15c78cc
--- /dev/null
+++ b/samples/bpf/xdpsock.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef XDPSOCK_H_
+#define XDPSOCK_H_
+
+#define MAX_SOCKS 4
+
+#endif /* XDPSOCK_H */
diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c
new file mode 100644
index 000000000000..a06177c262cd
--- /dev/null
+++ b/samples/bpf/xdpsock_kern.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#include "xdpsock.h"
+
+/* This XDP program is only needed for the XDP_SHARED_UMEM mode.
+ * If you do not use this mode, libbpf can supply an XDP program for you.
+ */
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, MAX_SOCKS);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} xsks_map SEC(".maps");
+
+static unsigned int rr;
+
+SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
+{
+	rr = (rr + 1) & (MAX_SOCKS - 1);
+
+	return bpf_redirect_map(&xsks_map, rr, XDP_DROP);
+}
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 405c4e091f8b..d3dba93dbab3 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -29,6 +29,7 @@
 
 #include "libbpf.h"
 #include "xsk.h"
+#include "xdpsock.h"
 #include <bpf/bpf.h>
 
 #ifndef SOL_XDP
@@ -47,7 +48,6 @@
 #define BATCH_SIZE 64
 
 #define DEBUG_HEXDUMP 0
-#define MAX_SOCKS 8
 
 typedef __u64 u64;
 typedef __u32 u32;
@@ -75,7 +75,8 @@ static u32 opt_xdp_bind_flags;
 static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 static int opt_timeout = 1000;
 static bool opt_need_wakeup = true;
-static __u32 prog_id;
+static u32 opt_num_xsks = 1;
+static u32 prog_id;
 
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
@@ -179,7 +180,7 @@ static void *poller(void *arg)
 
 static void remove_xdp_program(void)
 {
-	__u32 curr_prog_id = 0;
+	u32 curr_prog_id = 0;
 
 	if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
 		printf("bpf_get_link_xdp_id failed\n");
@@ -196,11 +197,11 @@ static void remove_xdp_program(void)
 static void int_exit(int sig)
 {
 	struct xsk_umem *umem = xsks[0]->umem->umem;
-
-	(void)sig;
+	int i;
 
 	dump_stats();
-	xsk_socket__delete(xsks[0]->xsk);
+	for (i = 0; i < num_socks; i++)
+		xsk_socket__delete(xsks[i]->xsk);
 	(void)xsk_umem__delete(umem);
 	remove_xdp_program();
 
@@ -290,8 +291,8 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
 		.flags = opt_umem_flags
 	};
-
-	int ret;
+	int ret, i;
+	u32 idx;
 
 	umem = calloc(1, sizeof(*umem));
 	if (!umem)
@@ -303,6 +304,15 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 	if (ret)
 		exit_with_error(-ret);
 
+	ret = xsk_ring_prod__reserve(&umem->fq,
+				     XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
+	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		exit_with_error(-ret);
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+		*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
+			i * opt_xsk_frame_size;
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+
 	umem->buffer = buffer;
 	return umem;
 }
@@ -312,8 +322,6 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	struct xsk_socket_config cfg;
 	struct xsk_socket_info *xsk;
 	int ret;
-	u32 idx;
-	int i;
 
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
@@ -322,11 +330,15 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	xsk->umem = umem;
 	cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-	cfg.libbpf_flags = 0;
+	if (opt_num_xsks > 1)
+		cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
+	else
+		cfg.libbpf_flags = 0;
 	cfg.xdp_flags = opt_xdp_flags;
 	cfg.bind_flags = opt_xdp_bind_flags;
-	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem,
-				 &xsk->rx, &xsk->tx, &cfg);
+
+	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue,
+				 umem->umem, &xsk->rx, &xsk->tx, &cfg);
 	if (ret)
 		exit_with_error(-ret);
 
@@ -334,17 +346,6 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	if (ret)
 		exit_with_error(-ret);
 
-	ret = xsk_ring_prod__reserve(&xsk->umem->fq,
-				     XSK_RING_PROD__DEFAULT_NUM_DESCS,
-				     &idx);
-	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
-		exit_with_error(-ret);
-	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
-		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) =
-			i * opt_xsk_frame_size;
-	xsk_ring_prod__submit(&xsk->umem->fq,
-			      XSK_RING_PROD__DEFAULT_NUM_DESCS);
-
 	return xsk;
 }
 
@@ -363,6 +364,7 @@ static struct option long_options[] = {
 	{"frame-size", required_argument, 0, 'f'},
 	{"no-need-wakeup", no_argument, 0, 'm'},
 	{"unaligned", no_argument, 0, 'u'},
+	{"shared-umem", no_argument, 0, 'M'},
 	{0, 0, 0, 0}
 };
 
@@ -386,6 +388,7 @@ static void usage(const char *prog)
 		"  -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n"
 		"  -f, --frame-size=n   Set the frame size (must be a power of two in aligned mode, default is %d).\n"
 		"  -u, --unaligned	Enable unaligned chunk placement\n"
+		"  -M, --shared-umem	Enable XDP_SHARED_UMEM\n"
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
 	exit(EXIT_FAILURE);
@@ -398,7 +401,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:mu",
+		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:muM",
 				long_options, &option_index);
 		if (c == -1)
 			break;
@@ -448,11 +451,14 @@ static void parse_command_line(int argc, char **argv)
 			break;
 		case 'f':
 			opt_xsk_frame_size = atoi(optarg);
+			break;
 		case 'm':
 			opt_need_wakeup = false;
 			opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP;
 			break;
-
+		case 'M':
+			opt_num_xsks = MAX_SOCKS;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -586,11 +592,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void rx_drop_all(void)
 {
-	struct pollfd fds[MAX_SOCKS + 1];
+	struct pollfd fds[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
-
 	for (i = 0; i < num_socks; i++) {
 		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLIN;
@@ -633,11 +637,10 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb)
 
 static void tx_only_all(void)
 {
-	struct pollfd fds[MAX_SOCKS];
+	struct pollfd fds[MAX_SOCKS] = {};
 	u32 frame_nb[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
 	for (i = 0; i < num_socks; i++) {
 		fds[0].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[0].events = POLLOUT;
@@ -706,11 +709,9 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void l2fwd_all(void)
 {
-	struct pollfd fds[MAX_SOCKS];
+	struct pollfd fds[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
-
 	for (i = 0; i < num_socks; i++) {
 		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLOUT | POLLIN;
@@ -728,13 +729,65 @@ static void l2fwd_all(void)
 	}
 }
 
+static void load_xdp_program(char **argv, struct bpf_object **obj)
+{
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type      = BPF_PROG_TYPE_XDP,
+	};
+	char xdp_filename[256];
+	int prog_fd;
+
+	snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
+	prog_load_attr.file = xdp_filename;
+
+	if (bpf_prog_load_xattr(&prog_load_attr, obj, &prog_fd))
+		exit(EXIT_FAILURE);
+	if (prog_fd < 0) {
+		fprintf(stderr, "ERROR: no program found: %s\n",
+			strerror(prog_fd));
+		exit(EXIT_FAILURE);
+	}
+
+	if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) {
+		fprintf(stderr, "ERROR: link set xdp fd failed\n");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void enter_xsks_into_map(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int i, xsks_map;
+
+	map = bpf_object__find_map_by_name(obj, "xsks_map");
+	xsks_map = bpf_map__fd(map);
+	if (xsks_map < 0) {
+		fprintf(stderr, "ERROR: no xsks map found: %s\n",
+			strerror(xsks_map));
+			exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < num_socks; i++) {
+		int fd = xsk_socket__fd(xsks[i]->xsk);
+		int key, ret;
+
+		key = i;
+		ret = bpf_map_update_elem(xsks_map, &key, &fd, 0);
+		if (ret) {
+			fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
+			exit(EXIT_FAILURE);
+		}
+	}
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	struct xsk_umem_info *umem;
+	struct bpf_object *obj;
 	pthread_t pt;
+	int i, ret;
 	void *bufs;
-	int ret;
 
 	parse_command_line(argc, argv);
 
@@ -744,6 +797,9 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	if (opt_num_xsks > 1)
+		load_xdp_program(argv, &obj);
+
 	/* Reserve memory for the umem. Use hugepages if unaligned chunk mode */
 	bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size,
 		    PROT_READ | PROT_WRITE,
@@ -752,16 +808,17 @@ int main(int argc, char **argv)
 		printf("ERROR: mmap failed\n");
 		exit(EXIT_FAILURE);
 	}
-       /* Create sockets... */
+
+	/* Create sockets... */
 	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
-	xsks[num_socks++] = xsk_configure_socket(umem);
+	for (i = 0; i < opt_num_xsks; i++)
+		xsks[num_socks++] = xsk_configure_socket(umem);
 
-	if (opt_bench == BENCH_TXONLY) {
-		int i;
+	for (i = 0; i < NUM_FRAMES; i++)
+		gen_eth_frame(umem, i * opt_xsk_frame_size);
 
-		for (i = 0; i < NUM_FRAMES; i++)
-			(void)gen_eth_frame(umem, i * opt_xsk_frame_size);
-	}
+	if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY)
+		enter_xsks_into_map(obj);
 
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);
-- 
cgit v1.2.3


From a68977d269dac0c7aa4a6f650b5e9191dd764861 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 7 Nov 2019 18:47:38 +0100
Subject: libbpf: Allow for creating Rx or Tx only AF_XDP sockets

The libbpf AF_XDP code is extended to allow for the creation of Rx
only or Tx only sockets. Previously it returned an error if the socket
was not initialized for both Rx and Tx.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: William Tu <u9012063@gmail.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/1573148860-30254-4-git-send-email-magnus.karlsson@intel.com
---
 tools/lib/bpf/xsk.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 8ebd810931ab..303ed633417b 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -562,7 +562,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	}
 
-	err = xsk_set_bpf_maps(xsk);
+	if (xsk->rx)
+		err = xsk_set_bpf_maps(xsk);
 	if (err) {
 		xsk_delete_bpf_maps(xsk);
 		close(xsk->prog_fd);
@@ -583,7 +584,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	struct xsk_socket *xsk;
 	int err;
 
-	if (!umem || !xsk_ptr || !rx || !tx)
+	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
 
 	xsk = calloc(1, sizeof(*xsk));
-- 
cgit v1.2.3


From 661842c46de2151758083b2ead605920b4770c2b Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 7 Nov 2019 18:47:39 +0100
Subject: samples/bpf: Use Rx-only and Tx-only sockets in xdpsock

Use Rx-only sockets for the rxdrop sample and Tx-only sockets for the
txpush sample in the xdpsock application. This so that we exercise and
show case these socket types too.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: William Tu <u9012063@gmail.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/1573148860-30254-5-git-send-email-magnus.karlsson@intel.com
---
 samples/bpf/xdpsock_user.c | 41 +++++++++++++++++++++++++++++------------
 1 file changed, 29 insertions(+), 12 deletions(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index d3dba93dbab3..a1f96e55e43a 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -291,8 +291,7 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
 		.flags = opt_umem_flags
 	};
-	int ret, i;
-	u32 idx;
+	int ret;
 
 	umem = calloc(1, sizeof(*umem));
 	if (!umem)
@@ -300,10 +299,18 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 
 	ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
 			       &cfg);
-
 	if (ret)
 		exit_with_error(-ret);
 
+	umem->buffer = buffer;
+	return umem;
+}
+
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
+{
+	int ret, i;
+	u32 idx;
+
 	ret = xsk_ring_prod__reserve(&umem->fq,
 				     XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
 	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
@@ -312,15 +319,15 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 		*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
 			i * opt_xsk_frame_size;
 	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
-
-	umem->buffer = buffer;
-	return umem;
 }
 
-static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
+static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
+						    bool rx, bool tx)
 {
 	struct xsk_socket_config cfg;
 	struct xsk_socket_info *xsk;
+	struct xsk_ring_cons *rxr;
+	struct xsk_ring_prod *txr;
 	int ret;
 
 	xsk = calloc(1, sizeof(*xsk));
@@ -337,8 +344,10 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	cfg.xdp_flags = opt_xdp_flags;
 	cfg.bind_flags = opt_xdp_bind_flags;
 
-	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue,
-				 umem->umem, &xsk->rx, &xsk->tx, &cfg);
+	rxr = rx ? &xsk->rx : NULL;
+	txr = tx ? &xsk->tx : NULL;
+	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem,
+				 rxr, txr, &cfg);
 	if (ret)
 		exit_with_error(-ret);
 
@@ -783,6 +792,7 @@ static void enter_xsks_into_map(struct bpf_object *obj)
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	bool rx = false, tx = false;
 	struct xsk_umem_info *umem;
 	struct bpf_object *obj;
 	pthread_t pt;
@@ -811,11 +821,18 @@ int main(int argc, char **argv)
 
 	/* Create sockets... */
 	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
+	if (opt_bench == BENCH_RXDROP || opt_bench == BENCH_L2FWD) {
+		rx = true;
+		xsk_populate_fill_ring(umem);
+	}
+	if (opt_bench == BENCH_L2FWD || opt_bench == BENCH_TXONLY)
+		tx = true;
 	for (i = 0; i < opt_num_xsks; i++)
-		xsks[num_socks++] = xsk_configure_socket(umem);
+		xsks[num_socks++] = xsk_configure_socket(umem, rx, tx);
 
-	for (i = 0; i < NUM_FRAMES; i++)
-		gen_eth_frame(umem, i * opt_xsk_frame_size);
+	if (opt_bench == BENCH_TXONLY)
+		for (i = 0; i < NUM_FRAMES; i++)
+			gen_eth_frame(umem, i * opt_xsk_frame_size);
 
 	if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY)
 		enter_xsks_into_map(obj);
-- 
cgit v1.2.3


From 57afa8b0cfa61f35d4175a66e0f0e38ce12a1db5 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 7 Nov 2019 18:47:40 +0100
Subject: xsk: Extend documentation for Rx|Tx-only sockets and shared umems

Add more documentation about the new Rx-only and Tx-only sockets in
libbpf and also how libbpf can now support shared umems. Also found
two pieces that could be improved in the text, that got fixed in this
commit.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: William Tu <u9012063@gmail.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/1573148860-30254-6-git-send-email-magnus.karlsson@intel.com
---
 Documentation/networking/af_xdp.rst | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst
index 7a4caaaf3a17..5bc55a4e3bce 100644
--- a/Documentation/networking/af_xdp.rst
+++ b/Documentation/networking/af_xdp.rst
@@ -295,7 +295,7 @@ round-robin example of distributing packets is shown below:
    {
 	rr = (rr + 1) & (MAX_SOCKS - 1);
 
-	return bpf_redirect_map(&xsks_map, rr, 0);
+	return bpf_redirect_map(&xsks_map, rr, XDP_DROP);
    }
 
 Note, that since there is only a single set of FILL and COMPLETION
@@ -304,6 +304,12 @@ to make sure that multiple processes or threads do not use these rings
 concurrently. There are no synchronization primitives in the
 libbpf code that protects multiple users at this point in time.
 
+Libbpf uses this mode if you create more than one socket tied to the
+same umem. However, note that you need to supply the
+XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD libbpf_flag with the
+xsk_socket__create calls and load your own XDP program as there is no
+built in one in libbpf that will route the traffic for you.
+
 XDP_USE_NEED_WAKEUP bind flag
 -----------------------------
 
@@ -355,10 +361,22 @@ to set the size of at least one of the RX and TX rings. If you set
 both, you will be able to both receive and send traffic from your
 application, but if you only want to do one of them, you can save
 resources by only setting up one of them. Both the FILL ring and the
-COMPLETION ring are mandatory if you have a UMEM tied to your socket,
-which is the normal case. But if the XDP_SHARED_UMEM flag is used, any
-socket after the first one does not have a UMEM and should in that
-case not have any FILL or COMPLETION rings created.
+COMPLETION ring are mandatory as you need to have a UMEM tied to your
+socket. But if the XDP_SHARED_UMEM flag is used, any socket after the
+first one does not have a UMEM and should in that case not have any
+FILL or COMPLETION rings created as the ones from the shared umem will
+be used. Note, that the rings are single-producer single-consumer, so
+do not try to access them from multiple processes at the same
+time. See the XDP_SHARED_UMEM section.
+
+In libbpf, you can create Rx-only and Tx-only sockets by supplying
+NULL to the rx and tx arguments, respectively, to the
+xsk_socket__create function.
+
+If you create a Tx-only socket, we recommend that you do not put any
+packets on the fill ring. If you do this, drivers might think you are
+going to receive something when you in fact will not, and this can
+negatively impact performance.
 
 XDP_UMEM_REG setsockopt
 -----------------------
-- 
cgit v1.2.3


From b7a0d65d80a0c5034b366392624397a0915b7556 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 7 Nov 2019 09:00:45 -0800
Subject: bpf, testing: Workaround a verifier failure for test_progs

With latest llvm compiler, running test_progs will have the following
verifier failure for test_sysctl_loop1.o:

  libbpf: load bpf program failed: Permission denied
  libbpf: -- BEGIN DUMP LOG ---
  libbpf:
  invalid indirect read from stack var_off (0x0; 0xff)+196 size 7
  ...
  libbpf: -- END LOG --
  libbpf: failed to load program 'cgroup/sysctl'
  libbpf: failed to load object 'test_sysctl_loop1.o'

The related bytecode looks as below:

  0000000000000308 LBB0_8:
      97:       r4 = r10
      98:       r4 += -288
      99:       r4 += r7
     100:       w8 &= 255
     101:       r1 = r10
     102:       r1 += -488
     103:       r1 += r8
     104:       r2 = 7
     105:       r3 = 0
     106:       call 106
     107:       w1 = w0
     108:       w1 += -1
     109:       if w1 > 6 goto -24 <LBB0_5>
     110:       w0 += w8
     111:       r7 += 8
     112:       w8 = w0
     113:       if r7 != 224 goto -17 <LBB0_8>

And source code:

     for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
             ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
                               tcp_mem + i);
             if (ret <= 0 || ret > MAX_ULONG_STR_LEN)
                     return 0;
             off += ret & MAX_ULONG_STR_LEN;
     }

Current verifier is not able to conclude that register w0 before '+'
at insn 110 has a range of 1 to 7 and thinks it is from 0 - 255. This
leads to more conservative range for w8 at insn 112, and later verifier
complaint.

Let us workaround this issue until we found a compiler and/or verifier
solution. The workaround in this patch is to make variable 'ret' volatile,
which will force a reload and then '&' operation to ensure better value
range. With this patch, I got the below byte code for the loop:

  0000000000000328 LBB0_9:
     101:       r4 = r10
     102:       r4 += -288
     103:       r4 += r7
     104:       w8 &= 255
     105:       r1 = r10
     106:       r1 += -488
     107:       r1 += r8
     108:       r2 = 7
     109:       r3 = 0
     110:       call 106
     111:       *(u32 *)(r10 - 64) = r0
     112:       r1 = *(u32 *)(r10 - 64)
     113:       if w1 s< 1 goto -28 <LBB0_5>
     114:       r1 = *(u32 *)(r10 - 64)
     115:       if w1 s> 7 goto -30 <LBB0_5>
     116:       r1 = *(u32 *)(r10 - 64)
     117:       w1 &= 7
     118:       w1 += w8
     119:       r7 += 8
     120:       w8 = w1
     121:       if r7 != 224 goto -21 <LBB0_9>

Insn 117 did the '&' operation and we got more precise value range
for 'w8' at insn 120. The test is happy then:

  #3/17 test_sysctl_loop1.o:OK

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191107170045.2503480-1-yhs@fb.com
---
 tools/testing/selftests/bpf/progs/test_sysctl_loop1.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
index 608a06871572..d22e438198cf 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
@@ -44,7 +44,10 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	unsigned long tcp_mem[TCP_MEM_LOOPS] = {};
 	char value[MAX_VALUE_STR_LEN];
 	unsigned char i, off = 0;
-	int ret;
+	/* a workaround to prevent compiler from generating
+	 * codes verifier cannot handle yet.
+	 */
+	volatile int ret;
 
 	if (ctx->write)
 		return 0;
-- 
cgit v1.2.3


From e47a179997ceee6864fbae620eee09ea9c345a4d Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Mon, 11 Nov 2019 17:17:28 +0100
Subject: bpf, testing: Add missing object file to TEST_FILES

When installing kselftests to its own directory and run the
test_lwt_ip_encap.sh it will complain that test_lwt_ip_encap.o can't be
found. Same with the test_tc_edt.sh test it will complain that
test_tc_edt.o can't be found.

  $ ./test_lwt_ip_encap.sh
  starting egress IPv4 encap test
  Error opening object test_lwt_ip_encap.o: No such file or directory
  Object hashing failed!
  Cannot initialize ELF context!
  Failed to parse eBPF program: Invalid argument

Rework to add test_lwt_ip_encap.o and test_tc_edt.o to TEST_FILES so the
object file gets installed when installing kselftest.

Fixes: 74b5a5968fe8 ("selftests/bpf: Replace test_progs and test_maps w/ general rule")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191111161728.8854-1-anders.roxell@linaro.org
---
 tools/testing/selftests/bpf/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index b334a6db15c1..b03dc2298fea 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -38,7 +38,8 @@ TEST_GEN_PROGS += test_progs-bpf_gcc
 endif
 
 TEST_GEN_FILES =
-TEST_FILES =
+TEST_FILES = test_lwt_ip_encap.o \
+	test_tc_edt.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
-- 
cgit v1.2.3


From b7b3fc8dd95bc02bd30680da258e09dda55270db Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 15 Nov 2019 13:37:22 +0100
Subject: bpf: Support doubleword alignment in bpf_jit_binary_alloc

Currently passing alignment greater than 4 to bpf_jit_binary_alloc does
not work: in such cases it silently aligns only to 4 bytes.

On s390, in order to load a constant from memory in a large (>512k) BPF
program, one must use lgrl instruction, whose memory operand must be
aligned on an 8-byte boundary.

This patch makes it possible to request 8-byte alignment from
bpf_jit_binary_alloc, and also makes it issue a warning when an
unsupported alignment is requested.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191115123722.58462-1-iii@linux.ibm.com
---
 include/linux/filter.h | 6 ++++--
 kernel/bpf/core.c      | 4 ++++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7a6f8f6f1da4..ad80e9c6111c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -515,10 +515,12 @@ struct sock_fprog_kern {
 	struct sock_filter	*filter;
 };
 
+/* Some arches need doubleword alignment for their instructions and/or data */
+#define BPF_IMAGE_ALIGNMENT 8
+
 struct bpf_binary_header {
 	u32 pages;
-	/* Some arches need word alignment for their instructions */
-	u8 image[] __aligned(4);
+	u8 image[] __aligned(BPF_IMAGE_ALIGNMENT);
 };
 
 struct bpf_prog {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c1fde0303280..99693f3c4e99 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -31,6 +31,7 @@
 #include <linux/rcupdate.h>
 #include <linux/perf_event.h>
 #include <linux/extable.h>
+#include <linux/log2.h>
 #include <asm/unaligned.h>
 
 /* Registers */
@@ -815,6 +816,9 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 	struct bpf_binary_header *hdr;
 	u32 size, hole, start, pages;
 
+	WARN_ON_ONCE(!is_power_of_2(alignment) ||
+		     alignment > BPF_IMAGE_ALIGNMENT);
+
 	/* Most of BPF filters are really small, but if some of them
 	 * fill a page, allow at least 128 extra bytes to insert a
 	 * random section of illegal instructions.
-- 
cgit v1.2.3


From fcf35131396ace1339e2ca89b45a6b12eed17105 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 14 Nov 2019 16:18:20 +0100
Subject: s390/bpf: Make sure JIT passes do not increase code size

The upcoming s390 branch length extension patches rely on "passes do
not increase code size" property in order to consistently choose between
short and long branches. Currently this property does not hold between
the first and the second passes for register save/restore sequences, as
well as various code fragments that depend on SEEN_* flags.

Generate the code during the first pass conservatively: assume register
save/restore sequences have the maximum possible length, and that all
SEEN_* flags are set.

Also refuse to JIT if this happens anyway (e.g. due to a bug), as this
might lead to verifier bypass once long branches are introduced.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191114151820.53222-1-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 74 +++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 66 insertions(+), 8 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 1115071c8ff7..7bddb27c81e3 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -304,6 +304,24 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	}							\
 })
 
+/*
+ * Return whether this is the first pass. The first pass is special, since we
+ * don't know any sizes yet, and thus must be conservative.
+ */
+static bool is_first_pass(struct bpf_jit *jit)
+{
+	return jit->size == 0;
+}
+
+/*
+ * Return whether this is the code generation pass. The code generation pass is
+ * special, since we should change as little as possible.
+ */
+static bool is_codegen_pass(struct bpf_jit *jit)
+{
+	return jit->prg_buf;
+}
+
 /*
  * Fill whole space with illegal instructions
  */
@@ -381,9 +399,18 @@ static int get_end(struct bpf_jit *jit, int start)
  */
 static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 {
-
+	const int last = 15, save_restore_size = 6;
 	int re = 6, rs;
 
+	if (is_first_pass(jit)) {
+		/*
+		 * We don't know yet which registers are used. Reserve space
+		 * conservatively.
+		 */
+		jit->prg += (last - re + 1) * save_restore_size;
+		return;
+	}
+
 	do {
 		rs = get_start(jit, re);
 		if (!rs)
@@ -394,7 +421,7 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 		else
 			restore_regs(jit, rs, re, stack_depth);
 		re++;
-	} while (re <= 15);
+	} while (re <= last);
 }
 
 /*
@@ -418,21 +445,21 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 	/* Save registers */
 	save_restore_regs(jit, REGS_SAVE, stack_depth);
 	/* Setup literal pool */
-	if (jit->seen & SEEN_LITERAL) {
+	if (is_first_pass(jit) || (jit->seen & SEEN_LITERAL)) {
 		/* basr %r13,0 */
 		EMIT2(0x0d00, REG_L, REG_0);
 		jit->base_ip = jit->prg;
 	}
 	/* Setup stack and backchain */
-	if (jit->seen & SEEN_STACK) {
-		if (jit->seen & SEEN_FUNC)
+	if (is_first_pass(jit) || (jit->seen & SEEN_STACK)) {
+		if (is_first_pass(jit) || (jit->seen & SEEN_FUNC))
 			/* lgr %w1,%r15 (backchain) */
 			EMIT4(0xb9040000, REG_W1, REG_15);
 		/* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
 		EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
 		/* aghi %r15,-STK_OFF */
 		EMIT4_IMM(0xa70b0000, REG_15, -(STK_OFF + stack_depth));
-		if (jit->seen & SEEN_FUNC)
+		if (is_first_pass(jit) || (jit->seen & SEEN_FUNC))
 			/* stg %w1,152(%r15) (backchain) */
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
@@ -468,7 +495,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	_EMIT2(0x07fe);
 
 	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable &&
-	    (jit->seen & SEEN_FUNC)) {
+	    (is_first_pass(jit) || (jit->seen & SEEN_FUNC))) {
 		jit->r1_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r1 thunk */
 		if (test_facility(35)) {
@@ -1275,6 +1302,34 @@ branch_oc:
 	return insn_count;
 }
 
+/*
+ * Return whether new i-th instruction address does not violate any invariant
+ */
+static bool bpf_is_new_addr_sane(struct bpf_jit *jit, int i)
+{
+	/* On the first pass anything goes */
+	if (is_first_pass(jit))
+		return true;
+
+	/* The codegen pass must not change anything */
+	if (is_codegen_pass(jit))
+		return jit->addrs[i] == jit->prg;
+
+	/* Passes in between must not increase code size */
+	return jit->addrs[i] >= jit->prg;
+}
+
+/*
+ * Update the address of i-th instruction
+ */
+static int bpf_set_addr(struct bpf_jit *jit, int i)
+{
+	if (!bpf_is_new_addr_sane(jit, i))
+		return -1;
+	jit->addrs[i] = jit->prg;
+	return 0;
+}
+
 /*
  * Compile eBPF program into s390x code
  */
@@ -1287,12 +1342,15 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
 	jit->prg = 0;
 
 	bpf_jit_prologue(jit, fp->aux->stack_depth);
+	if (bpf_set_addr(jit, 0) < 0)
+		return -1;
 	for (i = 0; i < fp->len; i += insn_count) {
 		insn_count = bpf_jit_insn(jit, fp, i, extra_pass);
 		if (insn_count < 0)
 			return -1;
 		/* Next instruction address */
-		jit->addrs[i + insn_count] = jit->prg;
+		if (bpf_set_addr(jit, i + insn_count) < 0)
+			return -1;
 	}
 	bpf_jit_epilogue(jit, fp->aux->stack_depth);
 
-- 
cgit v1.2.3


From 110b2263db8ab91d204378988ca73b932b26dad3 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Thu, 14 Nov 2019 08:28:46 -0800
Subject: samples/bpf: Remove duplicate option from xdpsock

The '-f' option is shown twice in the usage(). This patch removes the
outdated version.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191114162847.221770-1-andre.guedes@intel.com
---
 samples/bpf/xdpsock_user.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index a1f96e55e43a..c5d0a006cafc 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -393,7 +393,6 @@ static void usage(const char *prog)
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
 		"  -z, --zero-copy      Force zero-copy mode.\n"
 		"  -c, --copy           Force copy mode.\n"
-		"  -f, --frame-size=n   Set the frame size (must be a power of two, default is %d).\n"
 		"  -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n"
 		"  -f, --frame-size=n   Set the frame size (must be a power of two in aligned mode, default is %d).\n"
 		"  -u, --unaligned	Enable unaligned chunk placement\n"
-- 
cgit v1.2.3


From b31333298087f8ee3559bd62bcbd1638f232cac0 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Thu, 14 Nov 2019 08:28:47 -0800
Subject: samples/bpf: Add missing option to xdpsock usage

Commit 743e568c1586 (samples/bpf: Add a "force" flag to XDP samples)
introduced the '-F' option but missed adding it to the usage() and the
'long_option' array.

Fixes: 743e568c1586 (samples/bpf: Add a "force" flag to XDP samples)
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191114162847.221770-2-andre.guedes@intel.com
---
 samples/bpf/xdpsock_user.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index c5d0a006cafc..a15480010828 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -374,6 +374,7 @@ static struct option long_options[] = {
 	{"no-need-wakeup", no_argument, 0, 'm'},
 	{"unaligned", no_argument, 0, 'u'},
 	{"shared-umem", no_argument, 0, 'M'},
+	{"force", no_argument, 0, 'F'},
 	{0, 0, 0, 0}
 };
 
@@ -397,6 +398,7 @@ static void usage(const char *prog)
 		"  -f, --frame-size=n   Set the frame size (must be a power of two in aligned mode, default is %d).\n"
 		"  -u, --unaligned	Enable unaligned chunk placement\n"
 		"  -M, --shared-umem	Enable XDP_SHARED_UMEM\n"
+		"  -F, --force		Force loading the XDP prog\n"
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
 	exit(EXIT_FAILURE);
-- 
cgit v1.2.3


From 808c9f7ebfffffc0a9a5d8aee1533759f09f93fc Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Thu, 14 Nov 2019 11:43:51 +0800
Subject: bpf, doc: Change right arguments for JIT example code

The example code for the x86_64 JIT uses the wrong arguments when
calling function bar().

Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191114034351.162740-1-maowenan@huawei.com
---
 Documentation/networking/filter.txt | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 319e5e041f38..c4a328f2d57a 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -770,10 +770,10 @@ Some core changes of the new internal format:
     callq foo
     mov %rax,%r13
     mov %rbx,%rdi
-    mov $0x2,%esi
-    mov $0x3,%edx
-    mov $0x4,%ecx
-    mov $0x5,%r8d
+    mov $0x6,%esi
+    mov $0x7,%edx
+    mov $0x8,%ecx
+    mov $0x9,%r8d
     callq bar
     add %r13,%rax
     mov -0x228(%rbp),%rbx
-- 
cgit v1.2.3


From c3d6324f841bab2403be6419986e2b1d1068d423 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 5 Jun 2019 10:48:37 +0200
Subject: x86/alternatives: Teach text_poke_bp() to emulate instructions

In preparation for static_call and variable size jump_label support,
teach text_poke_bp() to emulate instructions, namely:

  JMP32, JMP8, CALL, NOP2, NOP_ATOMIC5, INT3

The current text_poke_bp() takes a @handler argument which is used as
a jump target when the temporary INT3 is hit by a different CPU.

When patching CALL instructions, this doesn't work because we'd miss
the PUSH of the return address. Instead, teach poke_int3_handler() to
emulate an instruction, typically the instruction we're patching in.

This fits almost all text_poke_bp() users, except
arch_unoptimize_kprobe() which restores random text, and for that site
we have to build an explicit emulate instruction.

Tested-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191111132457.529086974@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 8c7eebc10687af45ac8e40ad1bac0cf7893dba9f)
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/include/asm/text-patching.h |  24 +++++--
 arch/x86/kernel/alternative.c        | 132 +++++++++++++++++++++++++++--------
 arch/x86/kernel/jump_label.c         |   9 +--
 arch/x86/kernel/kprobes/opt.c        |  11 ++-
 4 files changed, 130 insertions(+), 46 deletions(-)

diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 5e8319bb207a..23c626a742e8 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -26,10 +26,11 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define POKE_MAX_OPCODE_SIZE	5
 
 struct text_poke_loc {
-	void *detour;
 	void *addr;
-	size_t len;
-	const char opcode[POKE_MAX_OPCODE_SIZE];
+	int len;
+	s32 rel32;
+	u8 opcode;
+	const u8 text[POKE_MAX_OPCODE_SIZE];
 };
 
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -51,8 +52,10 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
-extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
 extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
+extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+			       const void *opcode, size_t len, const void *emulate);
 extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
@@ -63,8 +66,17 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 
-#define INT3_INSN_SIZE 1
-#define CALL_INSN_SIZE 5
+#define INT3_INSN_SIZE		1
+#define INT3_INSN_OPCODE	0xCC
+
+#define CALL_INSN_SIZE		5
+#define CALL_INSN_OPCODE	0xE8
+
+#define JMP32_INSN_SIZE		5
+#define JMP32_INSN_OPCODE	0xE9
+
+#define JMP8_INSN_SIZE		2
+#define JMP8_INSN_OPCODE	0xEB
 
 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9d3a971ea364..9ec463fe96f2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -956,16 +956,15 @@ NOKPROBE_SYMBOL(patch_cmp);
 int poke_int3_handler(struct pt_regs *regs)
 {
 	struct text_poke_loc *tp;
-	unsigned char int3 = 0xcc;
 	void *ip;
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
 	 * bp_patching.nr_entries.
 	 *
-	 * 	nr_entries != 0			INT3
-	 * 	WMB				RMB
-	 * 	write INT3			if (nr_entries)
+	 *	nr_entries != 0			INT3
+	 *	WMB				RMB
+	 *	write INT3			if (nr_entries)
 	 *
 	 * Idem for other elements in bp_patching.
 	 */
@@ -978,9 +977,9 @@ int poke_int3_handler(struct pt_regs *regs)
 		return 0;
 
 	/*
-	 * Discount the sizeof(int3). See text_poke_bp_batch().
+	 * Discount the INT3. See text_poke_bp_batch().
 	 */
-	ip = (void *) regs->ip - sizeof(int3);
+	ip = (void *) regs->ip - INT3_INSN_SIZE;
 
 	/*
 	 * Skip the binary search if there is a single member in the vector.
@@ -997,8 +996,28 @@ int poke_int3_handler(struct pt_regs *regs)
 			return 0;
 	}
 
-	/* set up the specified breakpoint detour */
-	regs->ip = (unsigned long) tp->detour;
+	ip += tp->len;
+
+	switch (tp->opcode) {
+	case INT3_INSN_OPCODE:
+		/*
+		 * Someone poked an explicit INT3, they'll want to handle it,
+		 * do not consume.
+		 */
+		return 0;
+
+	case CALL_INSN_OPCODE:
+		int3_emulate_call(regs, (long)ip + tp->rel32);
+		break;
+
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		int3_emulate_jmp(regs, (long)ip + tp->rel32);
+		break;
+
+	default:
+		BUG();
+	}
 
 	return 1;
 }
@@ -1014,7 +1033,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  * synchronization using int3 breakpoint.
  *
  * The way it is done:
- * 	- For each entry in the vector:
+ *	- For each entry in the vector:
  *		- add a int3 trap to the address that will be patched
  *	- sync cores
  *	- For each entry in the vector:
@@ -1027,9 +1046,9 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  */
 void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
-	int patched_all_but_first = 0;
-	unsigned char int3 = 0xcc;
+	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
+	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
@@ -1053,16 +1072,16 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	/*
 	 * Second step: update all but the first byte of the patched range.
 	 */
-	for (i = 0; i < nr_entries; i++) {
+	for (do_sync = 0, i = 0; i < nr_entries; i++) {
 		if (tp[i].len - sizeof(int3) > 0) {
 			text_poke((char *)tp[i].addr + sizeof(int3),
-				  (const char *)tp[i].opcode + sizeof(int3),
+				  (const char *)tp[i].text + sizeof(int3),
 				  tp[i].len - sizeof(int3));
-			patched_all_but_first++;
+			do_sync++;
 		}
 	}
 
-	if (patched_all_but_first) {
+	if (do_sync) {
 		/*
 		 * According to Intel, this core syncing is very likely
 		 * not necessary and we'd be safe even without it. But
@@ -1075,10 +1094,17 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	 * Third step: replace the first byte (int3) by the first byte of
 	 * replacing opcode.
 	 */
-	for (i = 0; i < nr_entries; i++)
-		text_poke(tp[i].addr, tp[i].opcode, sizeof(int3));
+	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		if (tp[i].text[0] == INT3_INSN_OPCODE)
+			continue;
+
+		text_poke(tp[i].addr, tp[i].text, sizeof(int3));
+		do_sync++;
+	}
+
+	if (do_sync)
+		on_each_cpu(do_sync_core, NULL, 1);
 
-	on_each_cpu(do_sync_core, NULL, 1);
 	/*
 	 * sync_core() implies an smp_mb() and orders this store against
 	 * the writing of the new instruction.
@@ -1087,6 +1113,60 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	bp_patching.nr_entries = 0;
 }
 
+void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+			const void *opcode, size_t len, const void *emulate)
+{
+	struct insn insn;
+
+	if (!opcode)
+		opcode = (void *)tp->text;
+	else
+		memcpy((void *)tp->text, opcode, len);
+
+	if (!emulate)
+		emulate = opcode;
+
+	kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
+	insn_get_length(&insn);
+
+	BUG_ON(!insn_complete(&insn));
+	BUG_ON(len != insn.length);
+
+	tp->addr = addr;
+	tp->len = len;
+	tp->opcode = insn.opcode.bytes[0];
+
+	switch (tp->opcode) {
+	case INT3_INSN_OPCODE:
+		break;
+
+	case CALL_INSN_OPCODE:
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		tp->rel32 = insn.immediate.value;
+		break;
+
+	default: /* assume NOP */
+		switch (len) {
+		case 2: /* NOP2 -- emulate as JMP8+0 */
+			BUG_ON(memcmp(emulate, ideal_nops[len], len));
+			tp->opcode = JMP8_INSN_OPCODE;
+			tp->rel32 = 0;
+			break;
+
+		case 5: /* NOP5 -- emulate as JMP32+0 */
+			BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+			tp->opcode = JMP32_INSN_OPCODE;
+			tp->rel32 = 0;
+			break;
+
+		default: /* unknown instruction */
+			BUG();
+		}
+		break;
+	}
+}
+
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP
  * @addr:	address to patch
@@ -1098,20 +1178,10 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
  * dynamically allocated memory. This function should be used when it is
  * not possible to allocate memory.
  */
-void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	struct text_poke_loc tp = {
-		.detour = handler,
-		.addr = addr,
-		.len = len,
-	};
-
-	if (len > POKE_MAX_OPCODE_SIZE) {
-		WARN_ONCE(1, "len is larger than %d\n", POKE_MAX_OPCODE_SIZE);
-		return;
-	}
-
-	memcpy((void *)tp.opcode, opcode, len);
+	struct text_poke_loc tp;
 
+	text_poke_loc_init(&tp, addr, opcode, len, emulate);
 	text_poke_bp_batch(&tp, 1);
 }
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 044053235302..c1a8b9e71408 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -89,8 +89,7 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 		return;
 	}
 
-	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE,
-		     (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
+	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL);
 }
 
 void arch_jump_label_transform(struct jump_entry *entry,
@@ -147,11 +146,9 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 	}
 
 	__jump_label_set_jump_code(entry, type,
-				   (union jump_code_union *) &tp->opcode, 0);
+				   (union jump_code_union *)&tp->text, 0);
 
-	tp->addr = entry_code;
-	tp->detour = entry_code + JUMP_LABEL_NOP_SIZE;
-	tp->len = JUMP_LABEL_NOP_SIZE;
+	text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL);
 
 	tp_vec_nr++;
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index b348dd506d58..8900329c28a7 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -437,8 +437,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
 		insn_buff[0] = RELATIVEJUMP_OPCODE;
 		*(s32 *)(&insn_buff[1]) = rel;
 
-		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-			     op->optinsn.insn);
+		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL);
 
 		list_del_init(&op->list);
 	}
@@ -448,12 +447,18 @@ void arch_optimize_kprobes(struct list_head *oplist)
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	u8 insn_buff[RELATIVEJUMP_SIZE];
+	u8 emulate_buff[RELATIVEJUMP_SIZE];
 
 	/* Set int3 to first byte for kprobes */
 	insn_buff[0] = BREAKPOINT_INSTRUCTION;
 	memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+	emulate_buff[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
 	text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-		     op->optinsn.insn);
+		     emulate_buff);
 }
 
 /*
-- 
cgit v1.2.3


From 3b2744e665206ea82ce7673cb3ec889b2898a267 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:02 -0800
Subject: bpf: Refactor x86 JIT into helpers

Refactor x86 JITing of LDX, STX, CALL instructions into separate helper
functions.  No functional changes in LDX and STX helpers.  There is a minor
change in CALL helper. It will populate target address correctly on the first
pass of JIT instead of second pass. That won't reduce total number of JIT
passes though.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-3-ast@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 152 ++++++++++++++++++++++++++++----------------
 1 file changed, 98 insertions(+), 54 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8cd23d8309bf..fb99d976ad6e 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -198,6 +198,8 @@ struct jit_context {
 /* Maximum number of bytes emitted while JITing one eBPF insn */
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
+/* number of bytes emit_call() needs to generate call instruction */
+#define X86_CALL_SIZE		5
 
 #define PROLOGUE_SIZE		20
 
@@ -390,6 +392,99 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
 	*pprog = prog;
 }
 
+/* LDX: dst_reg = *(u8*)(src_reg + off) */
+static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	switch (size) {
+	case BPF_B:
+		/* Emit 'movzx rax, byte ptr [rax + off]' */
+		EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
+		break;
+	case BPF_H:
+		/* Emit 'movzx rax, word ptr [rax + off]' */
+		EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
+		break;
+	case BPF_W:
+		/* Emit 'mov eax, dword ptr [rax+0x14]' */
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
+		else
+			EMIT1(0x8B);
+		break;
+	case BPF_DW:
+		/* Emit 'mov rax, qword ptr [rax+0x14]' */
+		EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
+		break;
+	}
+	/*
+	 * If insn->off == 0 we can save one extra byte, but
+	 * special case of x86 R13 which always needs an offset
+	 * is not worth the hassle
+	 */
+	if (is_imm8(off))
+		EMIT2(add_2reg(0x40, src_reg, dst_reg), off);
+	else
+		EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off);
+	*pprog = prog;
+}
+
+/* STX: *(u8*)(dst_reg + off) = src_reg */
+static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	switch (size) {
+	case BPF_B:
+		/* Emit 'mov byte ptr [rax + off], al' */
+		if (is_ereg(dst_reg) || is_ereg(src_reg) ||
+		    /* We have to add extra byte for x86 SIL, DIL regs */
+		    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
+			EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
+		else
+			EMIT1(0x88);
+		break;
+	case BPF_H:
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
+		else
+			EMIT2(0x66, 0x89);
+		break;
+	case BPF_W:
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
+		else
+			EMIT1(0x89);
+		break;
+	case BPF_DW:
+		EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
+		break;
+	}
+	if (is_imm8(off))
+		EMIT2(add_2reg(0x40, dst_reg, src_reg), off);
+	else
+		EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off);
+	*pprog = prog;
+}
+
+static int emit_call(u8 **pprog, void *func, void *ip)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	s64 offset;
+
+	offset = func - (ip + X86_CALL_SIZE);
+	if (!is_simm32(offset)) {
+		pr_err("Target call %p is out of range\n", func);
+		return -EINVAL;
+	}
+	EMIT1_off32(0xE8, offset);
+	*pprog = prog;
+	return 0;
+}
 
 static bool ex_handler_bpf(const struct exception_table_entry *x,
 			   struct pt_regs *regs, int trapnr,
@@ -773,68 +868,22 @@ st:			if (is_imm8(insn->off))
 
 			/* STX: *(u8*)(dst_reg + off) = src_reg */
 		case BPF_STX | BPF_MEM | BPF_B:
-			/* Emit 'mov byte ptr [rax + off], al' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
-			    /* We have to add extra byte for x86 SIL, DIL regs */
-			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
-				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
-			else
-				EMIT1(0x88);
-			goto stx;
 		case BPF_STX | BPF_MEM | BPF_H:
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
-			else
-				EMIT2(0x66, 0x89);
-			goto stx;
 		case BPF_STX | BPF_MEM | BPF_W:
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
-			else
-				EMIT1(0x89);
-			goto stx;
 		case BPF_STX | BPF_MEM | BPF_DW:
-			EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
-stx:			if (is_imm8(insn->off))
-				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
-			else
-				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
-					    insn->off);
+			emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			break;
 
 			/* LDX: dst_reg = *(u8*)(src_reg + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
-			/* Emit 'movzx rax, byte ptr [rax + off]' */
-			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
-			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_H:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
-			/* Emit 'movzx rax, word ptr [rax + off]' */
-			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
-			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_W:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
-			/* Emit 'mov eax, dword ptr [rax+0x14]' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
-			else
-				EMIT1(0x8B);
-			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
-			/* Emit 'mov rax, qword ptr [rax+0x14]' */
-			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
-ldx:			/*
-			 * If insn->off == 0 we can save one extra byte, but
-			 * special case of x86 R13 which always needs an offset
-			 * is not worth the hassle
-			 */
-			if (is_imm8(insn->off))
-				EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off);
-			else
-				EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
-					    insn->off);
+			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
 				struct exception_table_entry *ex;
 				u8 *_insn = image + proglen;
@@ -899,13 +948,8 @@ xadd:			if (is_imm8(insn->off))
 			/* call */
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
-			jmp_offset = func - (image + addrs[i]);
-			if (!imm32 || !is_simm32(jmp_offset)) {
-				pr_err("unsupported BPF func %d addr %p image %p\n",
-				       imm32, func, image);
+			if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
 				return -EINVAL;
-			}
-			EMIT1_off32(0xE8, jmp_offset);
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
-- 
cgit v1.2.3


From 5964b2000f283ff5df366f718e0f083ebbaae977 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:03 -0800
Subject: bpf: Add bpf_arch_text_poke() helper

Add bpf_arch_text_poke() helper that is used by BPF trampoline logic to patch
nops/calls in kernel text into calls into BPF trampoline and to patch
calls/nops inside BPF programs too.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-4-ast@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 51 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/bpf.h         |  8 +++++++
 kernel/bpf/core.c           |  6 ++++++
 3 files changed, 65 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index fb99d976ad6e..254b2889e881 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -9,9 +9,11 @@
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
+#include <linux/memory.h>
 #include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
+#include <asm/text-patching.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -486,6 +488,55 @@ static int emit_call(u8 **pprog, void *func, void *ip)
 	return 0;
 }
 
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+		       void *old_addr, void *new_addr)
+{
+	u8 old_insn[X86_CALL_SIZE] = {};
+	u8 new_insn[X86_CALL_SIZE] = {};
+	u8 *prog;
+	int ret;
+
+	if (!is_kernel_text((long)ip))
+		/* BPF trampoline in modules is not supported */
+		return -EINVAL;
+
+	if (old_addr) {
+		prog = old_insn;
+		ret = emit_call(&prog, old_addr, (void *)ip);
+		if (ret)
+			return ret;
+	}
+	if (new_addr) {
+		prog = new_insn;
+		ret = emit_call(&prog, new_addr, (void *)ip);
+		if (ret)
+			return ret;
+	}
+	ret = -EBUSY;
+	mutex_lock(&text_mutex);
+	switch (t) {
+	case BPF_MOD_NOP_TO_CALL:
+		if (memcmp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE))
+			goto out;
+		text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL);
+		break;
+	case BPF_MOD_CALL_TO_CALL:
+		if (memcmp(ip, old_insn, X86_CALL_SIZE))
+			goto out;
+		text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL);
+		break;
+	case BPF_MOD_CALL_TO_NOP:
+		if (memcmp(ip, old_insn, X86_CALL_SIZE))
+			goto out;
+		text_poke_bp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE, NULL);
+		break;
+	}
+	ret = 0;
+out:
+	mutex_unlock(&text_mutex);
+	return ret;
+}
+
 static bool ex_handler_bpf(const struct exception_table_entry *x,
 			   struct pt_regs *regs, int trapnr,
 			   unsigned long error_code, unsigned long fault_addr)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7c7f518811a6..8b90db25348a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1157,4 +1157,12 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
 }
 #endif /* CONFIG_INET */
 
+enum bpf_text_poke_type {
+	BPF_MOD_NOP_TO_CALL,
+	BPF_MOD_CALL_TO_CALL,
+	BPF_MOD_CALL_TO_NOP,
+};
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+		       void *addr1, void *addr2);
+
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 99693f3c4e99..434a0d920153 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2144,6 +2144,12 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
 	return -EFAULT;
 }
 
+int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+			      void *addr1, void *addr2)
+{
+	return -ENOTSUPP;
+}
+
 DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 EXPORT_SYMBOL(bpf_stats_enabled_key);
 
-- 
cgit v1.2.3


From fec56f5890d93fc2ed74166c397dc186b1c25951 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:04 -0800
Subject: bpf: Introduce BPF trampoline

Introduce BPF trampoline concept to allow kernel code to call into BPF programs
with practically zero overhead.  The trampoline generation logic is
architecture dependent.  It's converting native calling convention into BPF
calling convention.  BPF ISA is 64-bit (even on 32-bit architectures). The
registers R1 to R5 are used to pass arguments into BPF functions. The main BPF
program accepts only single argument "ctx" in R1. Whereas CPU native calling
convention is different. x86-64 is passing first 6 arguments in registers
and the rest on the stack. x86-32 is passing first 3 arguments in registers.
sparc64 is passing first 6 in registers. And so on.

The trampolines between BPF and kernel already exist.  BPF_CALL_x macros in
include/linux/filter.h statically compile trampolines from BPF into kernel
helpers. They convert up to five u64 arguments into kernel C pointers and
integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On
32-bit architecture they're meaningful.

The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and
__bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert
kernel function arguments into array of u64s that BPF program consumes via
R1=ctx pointer.

This patch set is doing the same job as __bpf_trace_##call() static
trampolines, but dynamically for any kernel function. There are ~22k global
kernel functions that are attachable via nop at function entry. The function
arguments and types are described in BTF.  The job of btf_distill_func_proto()
function is to extract useful information from BTF into "function model" that
architecture dependent trampoline generators will use to generate assembly code
to cast kernel function arguments into array of u64s.  For example the kernel
function eth_type_trans has two pointers. They will be casted to u64 and stored
into stack of generated trampoline. The pointer to that stack space will be
passed into BPF program in R1. On x86-64 such generated trampoline will consume
16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will
make sure that only two u64 are accessed read-only by BPF program. The verifier
will also recognize the precise type of the pointers being accessed and will
not allow typecasting of the pointer to a different type within BPF program.

The tracing use case in the datacenter demonstrated that certain key kernel
functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always
active.  Other functions have both kprobe and kretprobe.  So it is essential to
keep both kernel code and BPF programs executing at maximum speed. Hence
generated BPF trampoline is re-generated every time new program is attached or
detached to maintain maximum performance.

To avoid the high cost of retpoline the attached BPF programs are called
directly. __bpf_prog_enter/exit() are used to support per-program execution
stats.  In the future this logic will be optimized further by adding support
for bpf_stats_enabled_key inside generated assembly code. Introduction of
preemptible and sleepable BPF programs will completely remove the need to call
to __bpf_prog_enter/exit().

Detach of a BPF program from the trampoline should not fail. To avoid memory
allocation in detach path the half of the page is used as a reserve and flipped
after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly
which is enough for BPF tracing use cases. This limit can be increased in the
future.

BPF_TRACE_FENTRY programs have access to raw kernel function arguments while
BPF_TRACE_FEXIT programs have access to kernel return value as well. Often
kprobe BPF program remembers function arguments in a map while kretprobe
fetches arguments from a map and analyzes them together with return value.
BPF_TRACE_FEXIT accelerates this typical use case.

Recursion prevention for kprobe BPF programs is done via per-cpu
bpf_prog_active counter. In practice that turned out to be a mistake. It
caused programs to randomly skip execution. The tracing tools missed results
they were looking for. Hence BPF trampoline doesn't provide builtin recursion
prevention. It's a job of BPF program itself and will be addressed in the
follow up patches.

BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases
in the future. For example to remove retpoline cost from XDP programs.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 211 +++++++++++++++++++++++++++++++++++-
 include/linux/bpf.h         | 105 ++++++++++++++++++
 include/uapi/linux/bpf.h    |   2 +
 kernel/bpf/Makefile         |   1 +
 kernel/bpf/btf.c            |  77 +++++++++++++-
 kernel/bpf/core.c           |   1 +
 kernel/bpf/syscall.c        |  53 +++++++++-
 kernel/bpf/trampoline.c     | 253 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c       |  42 ++++++++
 9 files changed, 735 insertions(+), 10 deletions(-)
 create mode 100644 kernel/bpf/trampoline.c

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 254b2889e881..be2b43a894f6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -98,6 +98,7 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 
 /* Pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_JIT_REG + 1)
+#define X86_REG_R9 (MAX_BPF_JIT_REG + 2)
 
 /*
  * The following table maps BPF registers to x86-64 registers.
@@ -106,8 +107,8 @@ static int bpf_size_to_x86_bytes(int bpf_size)
  * register in load/store instructions, it always needs an
  * extra byte of encoding and is callee saved.
  *
- * Also x86-64 register R9 is unused. x86-64 register R10 is
- * used for blinding (if enabled).
+ * x86-64 register R9 is not used by BPF programs, but can be used by BPF
+ * trampoline. x86-64 register R10 is used for blinding (if enabled).
  */
 static const int reg2hex[] = {
 	[BPF_REG_0] = 0,  /* RAX */
@@ -123,6 +124,7 @@ static const int reg2hex[] = {
 	[BPF_REG_FP] = 5, /* RBP readonly */
 	[BPF_REG_AX] = 2, /* R10 temp register */
 	[AUX_REG] = 3,    /* R11 temp register */
+	[X86_REG_R9] = 1, /* R9 register, 6th function argument */
 };
 
 static const int reg2pt_regs[] = {
@@ -150,6 +152,7 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_7) |
 			     BIT(BPF_REG_8) |
 			     BIT(BPF_REG_9) |
+			     BIT(X86_REG_R9) |
 			     BIT(BPF_REG_AX));
 }
 
@@ -1233,6 +1236,210 @@ emit_jmp:
 	return proglen;
 }
 
+static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+		      int stack_size)
+{
+	int i;
+	/* Store function arguments to stack.
+	 * For a function that accepts two pointers the sequence will be:
+	 * mov QWORD PTR [rbp-0x10],rdi
+	 * mov QWORD PTR [rbp-0x8],rsi
+	 */
+	for (i = 0; i < min(nr_args, 6); i++)
+		emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]),
+			 BPF_REG_FP,
+			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
+			 -(stack_size - i * 8));
+}
+
+static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+			 int stack_size)
+{
+	int i;
+
+	/* Restore function arguments from stack.
+	 * For a function that accepts two pointers the sequence will be:
+	 * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10]
+	 * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8]
+	 */
+	for (i = 0; i < min(nr_args, 6); i++)
+		emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]),
+			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
+			 BPF_REG_FP,
+			 -(stack_size - i * 8));
+}
+
+static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
+		      struct bpf_prog **progs, int prog_cnt, int stack_size)
+{
+	u8 *prog = *pprog;
+	int cnt = 0, i;
+
+	for (i = 0; i < prog_cnt; i++) {
+		if (emit_call(&prog, __bpf_prog_enter, prog))
+			return -EINVAL;
+		/* remember prog start time returned by __bpf_prog_enter */
+		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+
+		/* arg1: lea rdi, [rbp - stack_size] */
+		EMIT4(0x48, 0x8D, 0x7D, -stack_size);
+		/* arg2: progs[i]->insnsi for interpreter */
+		if (!progs[i]->jited)
+			emit_mov_imm64(&prog, BPF_REG_2,
+				       (long) progs[i]->insnsi >> 32,
+				       (u32) (long) progs[i]->insnsi);
+		/* call JITed bpf program or interpreter */
+		if (emit_call(&prog, progs[i]->bpf_func, prog))
+			return -EINVAL;
+
+		/* arg1: mov rdi, progs[i] */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32,
+			       (u32) (long) progs[i]);
+		/* arg2: mov rsi, rbx <- start time in nsec */
+		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+		if (emit_call(&prog, __bpf_prog_exit, prog))
+			return -EINVAL;
+	}
+	*pprog = prog;
+	return 0;
+}
+
+/* Example:
+ * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
+ * its 'struct btf_func_model' will be nr_args=2
+ * The assembly code when eth_type_trans is executing after trampoline:
+ *
+ * push rbp
+ * mov rbp, rsp
+ * sub rsp, 16                     // space for skb and dev
+ * push rbx                        // temp regs to pass start time
+ * mov qword ptr [rbp - 16], rdi   // save skb pointer to stack
+ * mov qword ptr [rbp - 8], rsi    // save dev pointer to stack
+ * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
+ * mov rbx, rax                    // remember start time in bpf stats are enabled
+ * lea rdi, [rbp - 16]             // R1==ctx of bpf prog
+ * call addr_of_jited_FENTRY_prog
+ * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
+ * mov rsi, rbx                    // prog start time
+ * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
+ * mov rdi, qword ptr [rbp - 16]   // restore skb pointer from stack
+ * mov rsi, qword ptr [rbp - 8]    // restore dev pointer from stack
+ * pop rbx
+ * leave
+ * ret
+ *
+ * eth_type_trans has 5 byte nop at the beginning. These 5 bytes will be
+ * replaced with 'call generated_bpf_trampoline'. When it returns
+ * eth_type_trans will continue executing with original skb and dev pointers.
+ *
+ * The assembly code when eth_type_trans is called from trampoline:
+ *
+ * push rbp
+ * mov rbp, rsp
+ * sub rsp, 24                     // space for skb, dev, return value
+ * push rbx                        // temp regs to pass start time
+ * mov qword ptr [rbp - 24], rdi   // save skb pointer to stack
+ * mov qword ptr [rbp - 16], rsi   // save dev pointer to stack
+ * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
+ * mov rbx, rax                    // remember start time if bpf stats are enabled
+ * lea rdi, [rbp - 24]             // R1==ctx of bpf prog
+ * call addr_of_jited_FENTRY_prog  // bpf prog can access skb and dev
+ * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
+ * mov rsi, rbx                    // prog start time
+ * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
+ * mov rdi, qword ptr [rbp - 24]   // restore skb pointer from stack
+ * mov rsi, qword ptr [rbp - 16]   // restore dev pointer from stack
+ * call eth_type_trans+5           // execute body of eth_type_trans
+ * mov qword ptr [rbp - 8], rax    // save return value
+ * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
+ * mov rbx, rax                    // remember start time in bpf stats are enabled
+ * lea rdi, [rbp - 24]             // R1==ctx of bpf prog
+ * call addr_of_jited_FEXIT_prog   // bpf prog can access skb, dev, return value
+ * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
+ * mov rsi, rbx                    // prog start time
+ * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
+ * mov rax, qword ptr [rbp - 8]    // restore eth_type_trans's return value
+ * pop rbx
+ * leave
+ * add rsp, 8                      // skip eth_type_trans's frame
+ * ret                             // return to its caller
+ */
+int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+				struct bpf_prog **fentry_progs, int fentry_cnt,
+				struct bpf_prog **fexit_progs, int fexit_cnt,
+				void *orig_call)
+{
+	int cnt = 0, nr_args = m->nr_args;
+	int stack_size = nr_args * 8;
+	u8 *prog;
+
+	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
+	if (nr_args > 6)
+		return -ENOTSUPP;
+
+	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
+	    (flags & BPF_TRAMP_F_SKIP_FRAME))
+		return -EINVAL;
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG)
+		stack_size += 8; /* room for return value of orig_call */
+
+	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+		/* skip patched call instruction and point orig_call to actual
+		 * body of the kernel function.
+		 */
+		orig_call += X86_CALL_SIZE;
+
+	prog = image;
+
+	EMIT1(0x55);		 /* push rbp */
+	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
+	EMIT1(0x53);		 /* push rbx */
+
+	save_regs(m, &prog, nr_args, stack_size);
+
+	if (fentry_cnt)
+		if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size))
+			return -EINVAL;
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		if (fentry_cnt)
+			restore_regs(m, &prog, nr_args, stack_size);
+
+		/* call original function */
+		if (emit_call(&prog, orig_call, prog))
+			return -EINVAL;
+		/* remember return value in a stack for bpf prog to access */
+		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+	}
+
+	if (fexit_cnt)
+		if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size))
+			return -EINVAL;
+
+	if (flags & BPF_TRAMP_F_RESTORE_REGS)
+		restore_regs(m, &prog, nr_args, stack_size);
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG)
+		/* restore original return value back into RAX */
+		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
+
+	EMIT1(0x5B); /* pop rbx */
+	EMIT1(0xC9); /* leave */
+	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+		/* skip our return address and return to parent */
+		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
+	EMIT1(0xC3); /* ret */
+	/* One half of the page has active running trampoline.
+	 * Another half is an area for next trampoline.
+	 * Make sure the trampoline generation logic doesn't overflow.
+	 */
+	if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY))
+		return -EFAULT;
+	return 0;
+}
+
 struct x64_jit_data {
 	struct bpf_binary_header *header;
 	int *addrs;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8b90db25348a..0d4c5c224d79 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -14,6 +14,8 @@
 #include <linux/numa.h>
 #include <linux/wait.h>
 #include <linux/u64_stats_sync.h>
+#include <linux/refcount.h>
+#include <linux/mutex.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -384,6 +386,100 @@ struct bpf_prog_stats {
 	struct u64_stats_sync syncp;
 } __aligned(2 * sizeof(u64));
 
+struct btf_func_model {
+	u8 ret_size;
+	u8 nr_args;
+	u8 arg_size[MAX_BPF_FUNC_ARGS];
+};
+
+/* Restore arguments before returning from trampoline to let original function
+ * continue executing. This flag is used for fentry progs when there are no
+ * fexit progs.
+ */
+#define BPF_TRAMP_F_RESTORE_REGS	BIT(0)
+/* Call original function after fentry progs, but before fexit progs.
+ * Makes sense for fentry/fexit, normal calls and indirect calls.
+ */
+#define BPF_TRAMP_F_CALL_ORIG		BIT(1)
+/* Skip current frame and return to parent.  Makes sense for fentry/fexit
+ * programs only. Should not be used with normal calls and indirect calls.
+ */
+#define BPF_TRAMP_F_SKIP_FRAME		BIT(2)
+
+/* Different use cases for BPF trampoline:
+ * 1. replace nop at the function entry (kprobe equivalent)
+ *    flags = BPF_TRAMP_F_RESTORE_REGS
+ *    fentry = a set of programs to run before returning from trampoline
+ *
+ * 2. replace nop at the function entry (kprobe + kretprobe equivalent)
+ *    flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME
+ *    orig_call = fentry_ip + MCOUNT_INSN_SIZE
+ *    fentry = a set of program to run before calling original function
+ *    fexit = a set of program to run after original function
+ *
+ * 3. replace direct call instruction anywhere in the function body
+ *    or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid)
+ *    With flags = 0
+ *      fentry = a set of programs to run before returning from trampoline
+ *    With flags = BPF_TRAMP_F_CALL_ORIG
+ *      orig_call = original callback addr or direct function addr
+ *      fentry = a set of program to run before calling original function
+ *      fexit = a set of program to run after original function
+ */
+int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+				struct bpf_prog **fentry_progs, int fentry_cnt,
+				struct bpf_prog **fexit_progs, int fexit_cnt,
+				void *orig_call);
+/* these two functions are called from generated trampoline */
+u64 notrace __bpf_prog_enter(void);
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
+
+enum bpf_tramp_prog_type {
+	BPF_TRAMP_FENTRY,
+	BPF_TRAMP_FEXIT,
+	BPF_TRAMP_MAX
+};
+
+struct bpf_trampoline {
+	/* hlist for trampoline_table */
+	struct hlist_node hlist;
+	/* serializes access to fields of this trampoline */
+	struct mutex mutex;
+	refcount_t refcnt;
+	u64 key;
+	struct {
+		struct btf_func_model model;
+		void *addr;
+	} func;
+	/* list of BPF programs using this trampoline */
+	struct hlist_head progs_hlist[BPF_TRAMP_MAX];
+	/* Number of attached programs. A counter per kind. */
+	int progs_cnt[BPF_TRAMP_MAX];
+	/* Executable image of trampoline */
+	void *image;
+	u64 selector;
+};
+#ifdef CONFIG_BPF_JIT
+struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
+int bpf_trampoline_link_prog(struct bpf_prog *prog);
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+void bpf_trampoline_put(struct bpf_trampoline *tr);
+#else
+static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+{
+	return NULL;
+}
+static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
+{
+	return -ENOTSUPP;
+}
+static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+{
+	return -ENOTSUPP;
+}
+static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
+#endif
+
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
@@ -398,6 +494,9 @@ struct bpf_prog_aux {
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	enum bpf_tramp_prog_type trampoline_prog_type;
+	struct bpf_trampoline *trampoline;
+	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
@@ -784,6 +883,12 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      u32 *next_btf_id);
 u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int);
 
+int btf_distill_func_proto(struct bpf_verifier_log *log,
+			   struct btf *btf,
+			   const struct btf_type *func_proto,
+			   const char *func_name,
+			   struct btf_func_model *m);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index df6809a76404..69c200e6e696 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -201,6 +201,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_GETSOCKOPT,
 	BPF_CGROUP_SETSOCKOPT,
 	BPF_TRACE_RAW_TP,
+	BPF_TRACE_FENTRY,
+	BPF_TRACE_FEXIT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e1d9adb212f9..3f671bf617e8 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4639c4ba9a9b..9e1164e5b429 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3517,13 +3517,18 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		args++;
 		nr_args--;
 	}
-	if (arg >= nr_args) {
+
+	if (prog->expected_attach_type == BPF_TRACE_FEXIT &&
+	    arg == nr_args) {
+		/* function return type */
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	} else if (arg >= nr_args) {
 		bpf_log(log, "func '%s' doesn't have %d-th argument\n",
-			tname, arg);
+			tname, arg + 1);
 		return false;
+	} else {
+		t = btf_type_by_id(btf_vmlinux, args[arg].type);
 	}
-
-	t = btf_type_by_id(btf_vmlinux, args[arg].type);
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf_vmlinux, t->type);
@@ -3784,6 +3789,70 @@ u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg)
 	return btf_id;
 }
 
+static int __get_type_size(struct btf *btf, u32 btf_id,
+			   const struct btf_type **bad_type)
+{
+	const struct btf_type *t;
+
+	if (!btf_id)
+		/* void */
+		return 0;
+	t = btf_type_by_id(btf, btf_id);
+	while (t && btf_type_is_modifier(t))
+		t = btf_type_by_id(btf, t->type);
+	if (!t)
+		return -EINVAL;
+	if (btf_type_is_ptr(t))
+		/* kernel size of pointer. Not BPF's size of pointer*/
+		return sizeof(void *);
+	if (btf_type_is_int(t) || btf_type_is_enum(t))
+		return t->size;
+	*bad_type = t;
+	return -EINVAL;
+}
+
+int btf_distill_func_proto(struct bpf_verifier_log *log,
+			   struct btf *btf,
+			   const struct btf_type *func,
+			   const char *tname,
+			   struct btf_func_model *m)
+{
+	const struct btf_param *args;
+	const struct btf_type *t;
+	u32 i, nargs;
+	int ret;
+
+	args = (const struct btf_param *)(func + 1);
+	nargs = btf_type_vlen(func);
+	if (nargs >= MAX_BPF_FUNC_ARGS) {
+		bpf_log(log,
+			"The function %s has %d arguments. Too many.\n",
+			tname, nargs);
+		return -EINVAL;
+	}
+	ret = __get_type_size(btf, func->type, &t);
+	if (ret < 0) {
+		bpf_log(log,
+			"The function %s return type %s is unsupported.\n",
+			tname, btf_kind_str[BTF_INFO_KIND(t->info)]);
+		return -EINVAL;
+	}
+	m->ret_size = ret;
+
+	for (i = 0; i < nargs; i++) {
+		ret = __get_type_size(btf, args[i].type, &t);
+		if (ret < 0) {
+			bpf_log(log,
+				"The function %s arg%d type %s is unsupported.\n",
+				tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]);
+			return -EINVAL;
+		}
+		m->arg_size[i] = ret;
+	}
+	m->nr_args = nargs;
+	return 0;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 434a0d920153..da5a8b8e278f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2015,6 +2015,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	if (aux->prog->has_callchain_buf)
 		put_callchain_buffers();
 #endif
+	bpf_trampoline_put(aux->trampoline);
 	for (i = 0; i < aux->func_cnt; i++)
 		bpf_jit_free(aux->func[i]);
 	if (aux->func_cnt) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6d9ce95e5a8d..e2e37bea86bc 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1799,6 +1799,49 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
+static int bpf_tracing_prog_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_prog *prog = filp->private_data;
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
+	bpf_prog_put(prog);
+	return 0;
+}
+
+static const struct file_operations bpf_tracing_prog_fops = {
+	.release	= bpf_tracing_prog_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
+};
+
+static int bpf_tracing_prog_attach(struct bpf_prog *prog)
+{
+	int tr_fd, err;
+
+	if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
+	    prog->expected_attach_type != BPF_TRACE_FEXIT) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	err = bpf_trampoline_link_prog(prog);
+	if (err)
+		goto out_put_prog;
+
+	tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops,
+				 prog, O_CLOEXEC);
+	if (tr_fd < 0) {
+		WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
+		err = tr_fd;
+		goto out_put_prog;
+	}
+	return tr_fd;
+
+out_put_prog:
+	bpf_prog_put(prog);
+	return err;
+}
+
 struct bpf_raw_tracepoint {
 	struct bpf_raw_event_map *btp;
 	struct bpf_prog *prog;
@@ -1850,14 +1893,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 
 	if (prog->type == BPF_PROG_TYPE_TRACING) {
 		if (attr->raw_tracepoint.name) {
-			/* raw_tp name should not be specified in raw_tp
-			 * programs that were verified via in-kernel BTF info
+			/* The attach point for this category of programs
+			 * should be specified via btf_id during program load.
 			 */
 			err = -EINVAL;
 			goto out_put_prog;
 		}
-		/* raw_tp name is taken from type name instead */
-		tp_name = prog->aux->attach_func_name;
+		if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
+			tp_name = prog->aux->attach_func_name;
+		else
+			return bpf_tracing_prog_attach(prog);
 	} else {
 		if (strncpy_from_user(buf,
 				      u64_to_user_ptr(attr->raw_tracepoint.name),
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
new file mode 100644
index 000000000000..10ae59d65f13
--- /dev/null
+++ b/kernel/bpf/trampoline.c
@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019 Facebook */
+#include <linux/hash.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+
+/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
+#define TRAMPOLINE_HASH_BITS 10
+#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS)
+
+static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
+
+/* serializes access to trampoline_table */
+static DEFINE_MUTEX(trampoline_mutex);
+
+struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+{
+	struct bpf_trampoline *tr;
+	struct hlist_head *head;
+	void *image;
+	int i;
+
+	mutex_lock(&trampoline_mutex);
+	head = &trampoline_table[hash_64(key, TRAMPOLINE_HASH_BITS)];
+	hlist_for_each_entry(tr, head, hlist) {
+		if (tr->key == key) {
+			refcount_inc(&tr->refcnt);
+			goto out;
+		}
+	}
+	tr = kzalloc(sizeof(*tr), GFP_KERNEL);
+	if (!tr)
+		goto out;
+
+	/* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (!image) {
+		kfree(tr);
+		tr = NULL;
+		goto out;
+	}
+
+	tr->key = key;
+	INIT_HLIST_NODE(&tr->hlist);
+	hlist_add_head(&tr->hlist, head);
+	refcount_set(&tr->refcnt, 1);
+	mutex_init(&tr->mutex);
+	for (i = 0; i < BPF_TRAMP_MAX; i++)
+		INIT_HLIST_HEAD(&tr->progs_hlist[i]);
+
+	set_vm_flush_reset_perms(image);
+	/* Keep image as writeable. The alternative is to keep flipping ro/rw
+	 * everytime new program is attached or detached.
+	 */
+	set_memory_x((long)image, 1);
+	tr->image = image;
+out:
+	mutex_unlock(&trampoline_mutex);
+	return tr;
+}
+
+/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
+ * bytes on x86.  Pick a number to fit into PAGE_SIZE / 2
+ */
+#define BPF_MAX_TRAMP_PROGS 40
+
+static int bpf_trampoline_update(struct bpf_trampoline *tr)
+{
+	void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
+	void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
+	struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS];
+	int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY];
+	int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT];
+	struct bpf_prog **progs, **fentry, **fexit;
+	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
+	struct bpf_prog_aux *aux;
+	int err;
+
+	if (fentry_cnt + fexit_cnt == 0) {
+		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL_TO_NOP,
+					 old_image, NULL);
+		tr->selector = 0;
+		goto out;
+	}
+
+	/* populate fentry progs */
+	fentry = progs = progs_to_run;
+	hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FENTRY], tramp_hlist)
+		*progs++ = aux->prog;
+
+	/* populate fexit progs */
+	fexit = progs;
+	hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FEXIT], tramp_hlist)
+		*progs++ = aux->prog;
+
+	if (fexit_cnt)
+		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
+
+	err = arch_prepare_bpf_trampoline(new_image, &tr->func.model, flags,
+					  fentry, fentry_cnt,
+					  fexit, fexit_cnt,
+					  tr->func.addr);
+	if (err)
+		goto out;
+
+	if (tr->selector)
+		/* progs already running at this address */
+		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL_TO_CALL,
+					 old_image, new_image);
+	else
+		/* first time registering */
+		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP_TO_CALL,
+					 NULL, new_image);
+	if (err)
+		goto out;
+	tr->selector++;
+out:
+	return err;
+}
+
+static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t)
+{
+	switch (t) {
+	case BPF_TRACE_FENTRY:
+		return BPF_TRAMP_FENTRY;
+	default:
+		return BPF_TRAMP_FEXIT;
+	}
+}
+
+int bpf_trampoline_link_prog(struct bpf_prog *prog)
+{
+	enum bpf_tramp_prog_type kind;
+	struct bpf_trampoline *tr;
+	int err = 0;
+
+	tr = prog->aux->trampoline;
+	kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
+	mutex_lock(&tr->mutex);
+	if (tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]
+	    >= BPF_MAX_TRAMP_PROGS) {
+		err = -E2BIG;
+		goto out;
+	}
+	if (!hlist_unhashed(&prog->aux->tramp_hlist)) {
+		/* prog already linked */
+		err = -EBUSY;
+		goto out;
+	}
+	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
+	tr->progs_cnt[kind]++;
+	err = bpf_trampoline_update(prog->aux->trampoline);
+	if (err) {
+		hlist_del(&prog->aux->tramp_hlist);
+		tr->progs_cnt[kind]--;
+	}
+out:
+	mutex_unlock(&tr->mutex);
+	return err;
+}
+
+/* bpf_trampoline_unlink_prog() should never fail. */
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+{
+	enum bpf_tramp_prog_type kind;
+	struct bpf_trampoline *tr;
+	int err;
+
+	tr = prog->aux->trampoline;
+	kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
+	mutex_lock(&tr->mutex);
+	hlist_del(&prog->aux->tramp_hlist);
+	tr->progs_cnt[kind]--;
+	err = bpf_trampoline_update(prog->aux->trampoline);
+	mutex_unlock(&tr->mutex);
+	return err;
+}
+
+void bpf_trampoline_put(struct bpf_trampoline *tr)
+{
+	if (!tr)
+		return;
+	mutex_lock(&trampoline_mutex);
+	if (!refcount_dec_and_test(&tr->refcnt))
+		goto out;
+	WARN_ON_ONCE(mutex_is_locked(&tr->mutex));
+	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FENTRY])))
+		goto out;
+	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
+		goto out;
+	bpf_jit_free_exec(tr->image);
+	hlist_del(&tr->hlist);
+	kfree(tr);
+out:
+	mutex_unlock(&trampoline_mutex);
+}
+
+/* The logic is similar to BPF_PROG_RUN, but with explicit rcu and preempt that
+ * are needed for trampoline. The macro is split into
+ * call _bpf_prog_enter
+ * call prog->bpf_func
+ * call __bpf_prog_exit
+ */
+u64 notrace __bpf_prog_enter(void)
+{
+	u64 start = 0;
+
+	rcu_read_lock();
+	preempt_disable();
+	if (static_branch_unlikely(&bpf_stats_enabled_key))
+		start = sched_clock();
+	return start;
+}
+
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+{
+	struct bpf_prog_stats *stats;
+
+	if (static_branch_unlikely(&bpf_stats_enabled_key) &&
+	    /* static_key could be enabled in __bpf_prog_enter
+	     * and disabled in __bpf_prog_exit.
+	     * And vice versa.
+	     * Hence check that 'start' is not zero.
+	     */
+	    start) {
+		stats = this_cpu_ptr(prog->aux->stats);
+		u64_stats_update_begin(&stats->syncp);
+		stats->cnt++;
+		stats->nsecs += sched_clock() - start;
+		u64_stats_update_end(&stats->syncp);
+	}
+	preempt_enable();
+	rcu_read_unlock();
+}
+
+int __weak
+arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+			    struct bpf_prog **fentry_progs, int fentry_cnt,
+			    struct bpf_prog **fexit_progs, int fexit_cnt,
+			    void *orig_call)
+{
+	return -ENOTSUPP;
+}
+
+static int __init init_trampolines(void)
+{
+	int i;
+
+	for (i = 0; i < TRAMPOLINE_TABLE_SIZE; i++)
+		INIT_HLIST_HEAD(&trampoline_table[i]);
+	return 0;
+}
+late_initcall(init_trampolines);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2f2374967b36..8f89cfa93e88 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9382,8 +9382,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	struct bpf_prog *prog = env->prog;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
+	struct bpf_trampoline *tr;
 	const struct btf_type *t;
 	const char *tname;
+	int ret = 0;
+	long addr;
 
 	if (prog->type != BPF_PROG_TYPE_TRACING)
 		return 0;
@@ -9432,6 +9435,45 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_proto = t;
 		prog->aux->attach_btf_trace = true;
 		return 0;
+	case BPF_TRACE_FENTRY:
+	case BPF_TRACE_FEXIT:
+		if (!btf_type_is_func(t)) {
+			verbose(env, "attach_btf_id %u is not a function\n",
+				btf_id);
+			return -EINVAL;
+		}
+		t = btf_type_by_id(btf_vmlinux, t->type);
+		if (!btf_type_is_func_proto(t))
+			return -EINVAL;
+		tr = bpf_trampoline_lookup(btf_id);
+		if (!tr)
+			return -ENOMEM;
+		prog->aux->attach_func_name = tname;
+		prog->aux->attach_func_proto = t;
+		mutex_lock(&tr->mutex);
+		if (tr->func.addr) {
+			prog->aux->trampoline = tr;
+			goto out;
+		}
+		ret = btf_distill_func_proto(&env->log, btf_vmlinux, t,
+					     tname, &tr->func.model);
+		if (ret < 0)
+			goto out;
+		addr = kallsyms_lookup_name(tname);
+		if (!addr) {
+			verbose(env,
+				"The address of function %s cannot be found\n",
+				tname);
+			ret = -ENOENT;
+			goto out;
+		}
+		tr->func.addr = (void *)addr;
+		prog->aux->trampoline = tr;
+out:
+		mutex_unlock(&tr->mutex);
+		if (ret)
+			bpf_trampoline_put(tr);
+		return ret;
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 1442e2871b7679271fc9fcbf043ba1be511a7428 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:05 -0800
Subject: libbpf: Introduce btf__find_by_name_kind()

Introduce btf__find_by_name_kind() helper to search BTF by name and kind, since
name alone can be ambiguous.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-6-ast@kernel.org
---
 tools/lib/bpf/btf.c      | 22 ++++++++++++++++++++++
 tools/lib/bpf/btf.h      |  2 ++
 tools/lib/bpf/libbpf.map |  1 +
 3 files changed, 25 insertions(+)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 86a1847e4a9f..88efa2bb7137 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -316,6 +316,28 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 	return -ENOENT;
 }
 
+__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
+			     __u32 kind)
+{
+	__u32 i;
+
+	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
+		return 0;
+
+	for (i = 1; i <= btf->nr_types; i++) {
+		const struct btf_type *t = btf->types[i];
+		const char *name;
+
+		if (btf_kind(t) != kind)
+			continue;
+		name = btf__name_by_offset(btf, t->name_off);
+		if (name && !strcmp(type_name, name))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
 void btf__free(struct btf *btf)
 {
 	if (!btf)
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index b18994116a44..d9ac73a02cde 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -72,6 +72,8 @@ LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
+LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
+					const char *type_name, __u32 kind);
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 9f39ee06b2d4..420e69bfe699 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -204,4 +204,5 @@ LIBBPF_0.0.6 {
 		bpf_program__is_tracing;
 		bpf_program__set_tracing;
 		bpf_program__size;
+		btf__find_by_name_kind;
 } LIBBPF_0.0.5;
-- 
cgit v1.2.3


From b8c54ea455dc2e0bda7ea9b0370279c224e21045 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:06 -0800
Subject: libbpf: Add support to attach to fentry/fexit tracing progs

Teach libbpf to recognize tracing programs types and attach them to
fentry/fexit.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-7-ast@kernel.org
---
 tools/include/uapi/linux/bpf.h |  2 +
 tools/lib/bpf/libbpf.c         | 99 +++++++++++++++++++++++++++++++-----------
 tools/lib/bpf/libbpf.h         |  4 ++
 tools/lib/bpf/libbpf.map       |  2 +
 4 files changed, 82 insertions(+), 25 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index df6809a76404..69c200e6e696 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -201,6 +201,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_GETSOCKOPT,
 	BPF_CGROUP_SETSOCKOPT,
 	BPF_TRACE_RAW_TP,
+	BPF_TRACE_FENTRY,
+	BPF_TRACE_FEXIT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 96ef18cfeffb..98ee033e021f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3856,7 +3856,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
-static int libbpf_attach_btf_id_by_name(const char *name, __u32 *btf_id);
+static int libbpf_attach_btf_id_by_name(const char *name,
+					enum bpf_attach_type attach_type);
 
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
@@ -3910,7 +3911,6 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	bpf_object__for_each_program(prog, obj) {
 		enum bpf_prog_type prog_type;
 		enum bpf_attach_type attach_type;
-		__u32 btf_id;
 
 		err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
 					       &attach_type);
@@ -3923,10 +3923,11 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		bpf_program__set_type(prog, prog_type);
 		bpf_program__set_expected_attach_type(prog, attach_type);
 		if (prog_type == BPF_PROG_TYPE_TRACING) {
-			err = libbpf_attach_btf_id_by_name(prog->section_name, &btf_id);
-			if (err)
+			err = libbpf_attach_btf_id_by_name(prog->section_name,
+							   attach_type);
+			if (err <= 0)
 				goto out;
-			prog->attach_btf_id = btf_id;
+			prog->attach_btf_id = err;
 		}
 	}
 
@@ -4935,6 +4936,10 @@ static const struct {
 	BPF_PROG_SEC("raw_tp/",			BPF_PROG_TYPE_RAW_TRACEPOINT),
 	BPF_PROG_BTF("tp_btf/",			BPF_PROG_TYPE_TRACING,
 						BPF_TRACE_RAW_TP),
+	BPF_PROG_BTF("fentry/",			BPF_PROG_TYPE_TRACING,
+						BPF_TRACE_FENTRY),
+	BPF_PROG_BTF("fexit/",			BPF_PROG_TYPE_TRACING,
+						BPF_TRACE_FEXIT),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
@@ -5052,43 +5057,56 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 }
 
 #define BTF_PREFIX "btf_trace_"
-static int libbpf_attach_btf_id_by_name(const char *name, __u32 *btf_id)
+int libbpf_find_vmlinux_btf_id(const char *name,
+			       enum bpf_attach_type attach_type)
 {
 	struct btf *btf = bpf_core_find_kernel_btf();
-	char raw_tp_btf_name[128] = BTF_PREFIX;
-	char *dst = raw_tp_btf_name + sizeof(BTF_PREFIX) - 1;
-	int ret, i, err = -EINVAL;
+	char raw_tp_btf[128] = BTF_PREFIX;
+	char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1;
+	const char *btf_name;
+	int err = -EINVAL;
+	u32 kind;
 
 	if (IS_ERR(btf)) {
 		pr_warn("vmlinux BTF is not found\n");
 		return -EINVAL;
 	}
 
+	if (attach_type == BPF_TRACE_RAW_TP) {
+		/* prepend "btf_trace_" prefix per kernel convention */
+		strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX));
+		btf_name = raw_tp_btf;
+		kind = BTF_KIND_TYPEDEF;
+	} else {
+		btf_name = name;
+		kind = BTF_KIND_FUNC;
+	}
+	err = btf__find_by_name_kind(btf, btf_name, kind);
+	btf__free(btf);
+	return err;
+}
+
+static int libbpf_attach_btf_id_by_name(const char *name,
+					enum bpf_attach_type attach_type)
+{
+	int i, err;
+
 	if (!name)
-		goto out;
+		return -EINVAL;
 
 	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
 		if (!section_names[i].is_attach_btf)
 			continue;
 		if (strncmp(name, section_names[i].sec, section_names[i].len))
 			continue;
-		/* prepend "btf_trace_" prefix per kernel convention */
-		strncat(dst, name + section_names[i].len,
-			sizeof(raw_tp_btf_name) - sizeof(BTF_PREFIX));
-		ret = btf__find_by_name(btf, raw_tp_btf_name);
-		if (ret <= 0) {
-			pr_warn("%s is not found in vmlinux BTF\n", dst);
-			goto out;
-		}
-		*btf_id = ret;
-		err = 0;
-		goto out;
+		err = libbpf_find_vmlinux_btf_id(name + section_names[i].len,
+						 attach_type);
+		if (err <= 0)
+			pr_warn("%s is not found in vmlinux BTF\n", name);
+		return err;
 	}
 	pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
-	err = -ESRCH;
-out:
-	btf__free(btf);
-	return err;
+	return -ESRCH;
 }
 
 int libbpf_attach_type_by_name(const char *name,
@@ -5716,6 +5734,37 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	return (struct bpf_link *)link;
 }
 
+struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+{
+	char errmsg[STRERR_BUFSIZE];
+	struct bpf_link_fd *link;
+	int prog_fd, pfd;
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("program '%s': can't attach before loaded\n",
+			bpf_program__title(prog, false));
+		return ERR_PTR(-EINVAL);
+	}
+
+	link = malloc(sizeof(*link));
+	if (!link)
+		return ERR_PTR(-ENOMEM);
+	link->link.destroy = &bpf_link__destroy_fd;
+
+	pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
+	if (pfd < 0) {
+		pfd = -errno;
+		free(link);
+		pr_warn("program '%s': failed to attach to trace: %s\n",
+			bpf_program__title(prog, false),
+			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+		return ERR_PTR(pfd);
+	}
+	link->fd = pfd;
+	return (struct bpf_link *)link;
+}
+
 enum bpf_perf_event_ret
 bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
 			   void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 5aa27caad6c2..fbff419f6daf 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -188,6 +188,8 @@ libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			 enum bpf_attach_type *expected_attach_type);
 LIBBPF_API int libbpf_attach_type_by_name(const char *name,
 					  enum bpf_attach_type *attach_type);
+LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name,
+					  enum bpf_attach_type attach_type);
 
 /* Accessors of bpf_program */
 struct bpf_program;
@@ -251,6 +253,8 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 				   const char *tp_name);
 
+LIBBPF_API struct bpf_link *
+bpf_program__attach_trace(struct bpf_program *prog);
 struct bpf_insn;
 
 /*
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 420e69bfe699..8ddc2c40e482 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -199,10 +199,12 @@ LIBBPF_0.0.6 {
 		bpf_map__set_pin_path;
 		bpf_object__open_file;
 		bpf_object__open_mem;
+		bpf_program__attach_trace;
 		bpf_program__get_expected_attach_type;
 		bpf_program__get_type;
 		bpf_program__is_tracing;
 		bpf_program__set_tracing;
 		bpf_program__size;
 		btf__find_by_name_kind;
+		libbpf_find_vmlinux_btf_id;
 } LIBBPF_0.0.5;
-- 
cgit v1.2.3


From e41074d39d71aa62a6ec557af09cd42ca0928e05 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:07 -0800
Subject: selftest/bpf: Simple test for fentry/fexit

Add simple test for fentry and fexit programs around eth_type_trans.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-8-ast@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/kfree_skb.c | 39 ++++++++++++++--
 tools/testing/selftests/bpf/progs/kfree_skb.c      | 52 ++++++++++++++++++++++
 2 files changed, 88 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 55d36856e621..7507c8f689bc 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -60,15 +60,17 @@ void test_kfree_skb(void)
 		.file = "./kfree_skb.o",
 	};
 
+	struct bpf_link *link = NULL, *link_fentry = NULL, *link_fexit = NULL;
+	struct bpf_map *perf_buf_map, *global_data;
+	struct bpf_program *prog, *fentry, *fexit;
 	struct bpf_object *obj, *obj2 = NULL;
 	struct perf_buffer_opts pb_opts = {};
 	struct perf_buffer *pb = NULL;
-	struct bpf_link *link = NULL;
-	struct bpf_map *perf_buf_map;
-	struct bpf_program *prog;
 	int err, kfree_skb_fd;
 	bool passed = false;
 	__u32 duration = 0;
+	const int zero = 0;
+	bool test_ok[2];
 
 	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
 			    &obj, &tattr.prog_fd);
@@ -82,9 +84,28 @@ void test_kfree_skb(void)
 	prog = bpf_object__find_program_by_title(obj2, "tp_btf/kfree_skb");
 	if (CHECK(!prog, "find_prog", "prog kfree_skb not found\n"))
 		goto close_prog;
+	fentry = bpf_object__find_program_by_title(obj2, "fentry/eth_type_trans");
+	if (CHECK(!fentry, "find_prog", "prog eth_type_trans not found\n"))
+		goto close_prog;
+	fexit = bpf_object__find_program_by_title(obj2, "fexit/eth_type_trans");
+	if (CHECK(!fexit, "find_prog", "prog eth_type_trans not found\n"))
+		goto close_prog;
+
+	global_data = bpf_object__find_map_by_name(obj2, "kfree_sk.bss");
+	if (CHECK(!global_data, "find global data", "not found\n"))
+		goto close_prog;
+
 	link = bpf_program__attach_raw_tracepoint(prog, NULL);
 	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
 		goto close_prog;
+	link_fentry = bpf_program__attach_trace(fentry);
+	if (CHECK(IS_ERR(link_fentry), "attach fentry", "err %ld\n",
+		  PTR_ERR(link_fentry)))
+		goto close_prog;
+	link_fexit = bpf_program__attach_trace(fexit);
+	if (CHECK(IS_ERR(link_fexit), "attach fexit", "err %ld\n",
+		  PTR_ERR(link_fexit)))
+		goto close_prog;
 
 	perf_buf_map = bpf_object__find_map_by_name(obj2, "perf_buf_map");
 	if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n"))
@@ -108,14 +129,26 @@ void test_kfree_skb(void)
 	err = perf_buffer__poll(pb, 100);
 	if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
 		goto close_prog;
+
 	/* make sure kfree_skb program was triggered
 	 * and it sent expected skb into ring buffer
 	 */
 	CHECK_FAIL(!passed);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(global_data), &zero, test_ok);
+	if (CHECK(err, "get_result",
+		  "failed to get output data: %d\n", err))
+		goto close_prog;
+
+	CHECK_FAIL(!test_ok[0] || !test_ok[1]);
 close_prog:
 	perf_buffer__free(pb);
 	if (!IS_ERR_OR_NULL(link))
 		bpf_link__destroy(link);
+	if (!IS_ERR_OR_NULL(link_fentry))
+		bpf_link__destroy(link_fentry);
+	if (!IS_ERR_OR_NULL(link_fexit))
+		bpf_link__destroy(link_fexit);
 	bpf_object__close(obj);
 	bpf_object__close(obj2);
 }
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index f769fdbf6725..dcc9feac8338 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
+#include <stdbool.h>
 #include "bpf_helpers.h"
 #include "bpf_endian.h"
 
@@ -116,3 +117,54 @@ int trace_kfree_skb(struct trace_kfree_skb *ctx)
 		       &meta, sizeof(meta));
 	return 0;
 }
+
+static volatile struct {
+	bool fentry_test_ok;
+	bool fexit_test_ok;
+} result;
+
+struct eth_type_trans_args {
+	struct sk_buff *skb;
+	struct net_device *dev;
+	unsigned short protocol; /* return value available to fexit progs */
+};
+
+SEC("fentry/eth_type_trans")
+int fentry_eth_type_trans(struct eth_type_trans_args *ctx)
+{
+	struct sk_buff *skb = ctx->skb;
+	struct net_device *dev = ctx->dev;
+	int len, ifindex;
+
+	__builtin_preserve_access_index(({
+		len = skb->len;
+		ifindex = dev->ifindex;
+	}));
+
+	/* fentry sees full packet including L2 header */
+	if (len != 74 || ifindex != 1)
+		return 0;
+	result.fentry_test_ok = true;
+	return 0;
+}
+
+SEC("fexit/eth_type_trans")
+int fexit_eth_type_trans(struct eth_type_trans_args *ctx)
+{
+	struct sk_buff *skb = ctx->skb;
+	struct net_device *dev = ctx->dev;
+	int len, ifindex;
+
+	__builtin_preserve_access_index(({
+		len = skb->len;
+		ifindex = dev->ifindex;
+	}));
+
+	/* fexit sees packet without L2 header that eth_type_trans should have
+	 * consumed.
+	 */
+	if (len != 60 || ctx->protocol != bpf_htons(0x86dd) || ifindex != 1)
+		return 0;
+	result.fexit_test_ok = true;
+	return 0;
+}
-- 
cgit v1.2.3


From faeb2dce084aff92d466c6ce68481989b815435b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:08 -0800
Subject: bpf: Add kernel test functions for fentry testing

Add few kernel functions with various number of arguments,
their types and sizes for BPF trampoline testing to cover
different calling conventions.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-9-ast@kernel.org
---
 net/bpf/test_run.c | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0be4497cb832..62933279fbba 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -105,6 +105,40 @@ out:
 	return err;
 }
 
+/* Integer types of various sizes and pointer combinations cover variety of
+ * architecture dependent calling conventions. 7+ can be supported in the
+ * future.
+ */
+int noinline bpf_fentry_test1(int a)
+{
+	return a + 1;
+}
+
+int noinline bpf_fentry_test2(int a, u64 b)
+{
+	return a + b;
+}
+
+int noinline bpf_fentry_test3(char a, int b, u64 c)
+{
+	return a + b + c;
+}
+
+int noinline bpf_fentry_test4(void *a, char b, int c, u64 d)
+{
+	return (long)a + b + c + d;
+}
+
+int noinline bpf_fentry_test5(u64 a, void *b, short c, int d, u64 e)
+{
+	return a + (long)b + c + d + e;
+}
+
+int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f)
+{
+	return a + (long)b + c + d + (long)e + f;
+}
+
 static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 			   u32 headroom, u32 tailroom)
 {
@@ -122,6 +156,13 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 		kfree(data);
 		return ERR_PTR(-EFAULT);
 	}
+	if (bpf_fentry_test1(1) != 2 ||
+	    bpf_fentry_test2(2, 3) != 5 ||
+	    bpf_fentry_test3(4, 5, 6) != 15 ||
+	    bpf_fentry_test4((void *)7, 8, 9, 10) != 34 ||
+	    bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 ||
+	    bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111)
+		return ERR_PTR(-EFAULT);
 	return data;
 }
 
-- 
cgit v1.2.3


From 11d1e2eefffe86339b3b0b773bd31ef3b88faf7d Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:09 -0800
Subject: selftests/bpf: Add test for BPF trampoline

Add sanity test for BPF trampoline that checks kernel functions
with up to 6 arguments of different sizes.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-10-ast@kernel.org
---
 tools/lib/bpf/bpf_helpers.h                        | 13 ++++
 .../testing/selftests/bpf/prog_tests/fentry_test.c | 64 +++++++++++++++
 tools/testing/selftests/bpf/progs/fentry_test.c    | 90 ++++++++++++++++++++++
 3 files changed, 167 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fentry_test.c
 create mode 100644 tools/testing/selftests/bpf/progs/fentry_test.c

diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 0c7d28292898..c63ab1add126 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -44,4 +44,17 @@ enum libbpf_pin_type {
 	LIBBPF_PIN_BY_NAME,
 };
 
+/* The following types should be used by BPF_PROG_TYPE_TRACING program to
+ * access kernel function arguments. BPF trampoline and raw tracepoints
+ * typecast arguments to 'unsigned long long'.
+ */
+typedef int __attribute__((aligned(8))) ks32;
+typedef char __attribute__((aligned(8))) ks8;
+typedef short __attribute__((aligned(8))) ks16;
+typedef long long __attribute__((aligned(8))) ks64;
+typedef unsigned int __attribute__((aligned(8))) ku32;
+typedef unsigned char __attribute__((aligned(8))) ku8;
+typedef unsigned short __attribute__((aligned(8))) ku16;
+typedef unsigned long long __attribute__((aligned(8))) ku64;
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
new file mode 100644
index 000000000000..9fb103193878
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+
+void test_fentry_test(void)
+{
+	struct bpf_prog_load_attr attr = {
+		.file = "./fentry_test.o",
+	};
+
+	char prog_name[] = "fentry/bpf_fentry_testX";
+	struct bpf_object *obj = NULL, *pkt_obj;
+	int err, pkt_fd, kfree_skb_fd, i;
+	struct bpf_link *link[6] = {};
+	struct bpf_program *prog[6];
+	__u32 duration, retval;
+	struct bpf_map *data_map;
+	const int zero = 0;
+	u64 result[6];
+
+	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &pkt_obj, &pkt_fd);
+	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+		return;
+	err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd);
+	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	for (i = 0; i < 6; i++) {
+		prog_name[sizeof(prog_name) - 2] = '1' + i;
+		prog[i] = bpf_object__find_program_by_title(obj, prog_name);
+		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name))
+			goto close_prog;
+		link[i] = bpf_program__attach_trace(prog[i]);
+		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
+			goto close_prog;
+	}
+	data_map = bpf_object__find_map_by_name(obj, "fentry_t.bss");
+	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
+		goto close_prog;
+
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "ipv6",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result);
+	if (CHECK(err, "get_result",
+		  "failed to get output data: %d\n", err))
+		goto close_prog;
+
+	for (i = 0; i < 6; i++)
+		if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
+			  i + 1, result[i]))
+			goto close_prog;
+
+close_prog:
+	for (i = 0; i < 6; i++)
+		if (!IS_ERR_OR_NULL(link[i]))
+			bpf_link__destroy(link[i]);
+	bpf_object__close(obj);
+	bpf_object__close(pkt_obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
new file mode 100644
index 000000000000..545788bf8d50
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct test1 {
+	ks32 a;
+};
+static volatile __u64 test1_result;
+SEC("fentry/bpf_fentry_test1")
+int test1(struct test1 *ctx)
+{
+	test1_result = ctx->a == 1;
+	return 0;
+}
+
+struct test2 {
+	ks32 a;
+	ku64 b;
+};
+static volatile __u64 test2_result;
+SEC("fentry/bpf_fentry_test2")
+int test2(struct test2 *ctx)
+{
+	test2_result = ctx->a == 2 && ctx->b == 3;
+	return 0;
+}
+
+struct test3 {
+	ks8 a;
+	ks32 b;
+	ku64 c;
+};
+static volatile __u64 test3_result;
+SEC("fentry/bpf_fentry_test3")
+int test3(struct test3 *ctx)
+{
+	test3_result = ctx->a == 4 && ctx->b == 5 && ctx->c == 6;
+	return 0;
+}
+
+struct test4 {
+	void *a;
+	ks8 b;
+	ks32 c;
+	ku64 d;
+};
+static volatile __u64 test4_result;
+SEC("fentry/bpf_fentry_test4")
+int test4(struct test4 *ctx)
+{
+	test4_result = ctx->a == (void *)7 && ctx->b == 8 && ctx->c == 9 &&
+		ctx->d == 10;
+	return 0;
+}
+
+struct test5 {
+	ku64 a;
+	void *b;
+	ks16 c;
+	ks32 d;
+	ku64 e;
+};
+static volatile __u64 test5_result;
+SEC("fentry/bpf_fentry_test5")
+int test5(struct test5 *ctx)
+{
+	test5_result = ctx->a == 11 && ctx->b == (void *)12 && ctx->c == 13 &&
+		ctx->d == 14 && ctx->e == 15;
+	return 0;
+}
+
+struct test6 {
+	ku64 a;
+	void *b;
+	ks16 c;
+	ks32 d;
+	void *e;
+	ks64 f;
+};
+static volatile __u64 test6_result;
+SEC("fentry/bpf_fentry_test6")
+int test6(struct test6 *ctx)
+{
+	test6_result = ctx->a == 16 && ctx->b == (void *)17 && ctx->c == 18 &&
+		ctx->d == 19 && ctx->e == (void *)20 && ctx->f == 21;
+	return 0;
+}
-- 
cgit v1.2.3


From d3b0856e5959fbb50a2f2f15a5614e20e51cb522 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:10 -0800
Subject: selftests/bpf: Add fexit tests for BPF trampoline

Add fexit tests for BPF trampoline that checks kernel functions
with up to 6 arguments of different sizes and their return values.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-11-ast@kernel.org
---
 .../testing/selftests/bpf/prog_tests/fexit_test.c  | 64 ++++++++++++++
 tools/testing/selftests/bpf/progs/fexit_test.c     | 98 ++++++++++++++++++++++
 2 files changed, 162 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fexit_test.c
 create mode 100644 tools/testing/selftests/bpf/progs/fexit_test.c

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
new file mode 100644
index 000000000000..f99013222c74
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+
+void test_fexit_test(void)
+{
+	struct bpf_prog_load_attr attr = {
+		.file = "./fexit_test.o",
+	};
+
+	char prog_name[] = "fexit/bpf_fentry_testX";
+	struct bpf_object *obj = NULL, *pkt_obj;
+	int err, pkt_fd, kfree_skb_fd, i;
+	struct bpf_link *link[6] = {};
+	struct bpf_program *prog[6];
+	__u32 duration, retval;
+	struct bpf_map *data_map;
+	const int zero = 0;
+	u64 result[6];
+
+	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &pkt_obj, &pkt_fd);
+	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+		return;
+	err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd);
+	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	for (i = 0; i < 6; i++) {
+		prog_name[sizeof(prog_name) - 2] = '1' + i;
+		prog[i] = bpf_object__find_program_by_title(obj, prog_name);
+		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name))
+			goto close_prog;
+		link[i] = bpf_program__attach_trace(prog[i]);
+		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
+			goto close_prog;
+	}
+	data_map = bpf_object__find_map_by_name(obj, "fexit_te.bss");
+	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
+		goto close_prog;
+
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "ipv6",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result);
+	if (CHECK(err, "get_result",
+		  "failed to get output data: %d\n", err))
+		goto close_prog;
+
+	for (i = 0; i < 6; i++)
+		if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
+			  i + 1, result[i]))
+			goto close_prog;
+
+close_prog:
+	for (i = 0; i < 6; i++)
+		if (!IS_ERR_OR_NULL(link[i]))
+			bpf_link__destroy(link[i]);
+	bpf_object__close(obj);
+	bpf_object__close(pkt_obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
new file mode 100644
index 000000000000..8b98b1a51784
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct test1 {
+	ks32 a;
+	ks32 ret;
+};
+static volatile __u64 test1_result;
+SEC("fexit/bpf_fentry_test1")
+int test1(struct test1 *ctx)
+{
+	test1_result = ctx->a == 1 && ctx->ret == 2;
+	return 0;
+}
+
+struct test2 {
+	ks32 a;
+	ku64 b;
+	ks32 ret;
+};
+static volatile __u64 test2_result;
+SEC("fexit/bpf_fentry_test2")
+int test2(struct test2 *ctx)
+{
+	test2_result = ctx->a == 2 && ctx->b == 3 && ctx->ret == 5;
+	return 0;
+}
+
+struct test3 {
+	ks8 a;
+	ks32 b;
+	ku64 c;
+	ks32 ret;
+};
+static volatile __u64 test3_result;
+SEC("fexit/bpf_fentry_test3")
+int test3(struct test3 *ctx)
+{
+	test3_result = ctx->a == 4 && ctx->b == 5 && ctx->c == 6 &&
+		ctx->ret == 15;
+	return 0;
+}
+
+struct test4 {
+	void *a;
+	ks8 b;
+	ks32 c;
+	ku64 d;
+	ks32 ret;
+};
+static volatile __u64 test4_result;
+SEC("fexit/bpf_fentry_test4")
+int test4(struct test4 *ctx)
+{
+	test4_result = ctx->a == (void *)7 && ctx->b == 8 && ctx->c == 9 &&
+		ctx->d == 10 && ctx->ret == 34;
+	return 0;
+}
+
+struct test5 {
+	ku64 a;
+	void *b;
+	ks16 c;
+	ks32 d;
+	ku64 e;
+	ks32 ret;
+};
+static volatile __u64 test5_result;
+SEC("fexit/bpf_fentry_test5")
+int test5(struct test5 *ctx)
+{
+	test5_result = ctx->a == 11 && ctx->b == (void *)12 && ctx->c == 13 &&
+		ctx->d == 14 && ctx->e == 15 && ctx->ret == 65;
+	return 0;
+}
+
+struct test6 {
+	ku64 a;
+	void *b;
+	ks16 c;
+	ks32 d;
+	void *e;
+	ks64 f;
+	ks32 ret;
+};
+static volatile __u64 test6_result;
+SEC("fexit/bpf_fentry_test6")
+int test6(struct test6 *ctx)
+{
+	test6_result = ctx->a == 16 && ctx->b == (void *)17 && ctx->c == 18 &&
+		ctx->d == 19 && ctx->e == (void *)20 && ctx->f == 21 &&
+		ctx->ret == 111;
+	return 0;
+}
-- 
cgit v1.2.3


From 510312882c4b583fcd4fdf972d00e9ce631ed188 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:11 -0800
Subject: selftests/bpf: Add combined fentry/fexit test

Add a combined fentry/fexit test.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-12-ast@kernel.org
---
 .../selftests/bpf/prog_tests/fentry_fexit.c        | 90 ++++++++++++++++++++++
 1 file changed, 90 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fentry_fexit.c

diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
new file mode 100644
index 000000000000..40bcff2cc274
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+
+void test_fentry_fexit(void)
+{
+	struct bpf_prog_load_attr attr_fentry = {
+		.file = "./fentry_test.o",
+	};
+	struct bpf_prog_load_attr attr_fexit = {
+		.file = "./fexit_test.o",
+	};
+
+	struct bpf_object *obj_fentry = NULL, *obj_fexit = NULL, *pkt_obj;
+	struct bpf_map *data_map_fentry, *data_map_fexit;
+	char fentry_name[] = "fentry/bpf_fentry_testX";
+	char fexit_name[] = "fexit/bpf_fentry_testX";
+	int err, pkt_fd, kfree_skb_fd, i;
+	struct bpf_link *link[12] = {};
+	struct bpf_program *prog[12];
+	__u32 duration, retval;
+	const int zero = 0;
+	u64 result[12];
+
+	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &pkt_obj, &pkt_fd);
+	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+		return;
+	err = bpf_prog_load_xattr(&attr_fentry, &obj_fentry, &kfree_skb_fd);
+	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
+		goto close_prog;
+	err = bpf_prog_load_xattr(&attr_fexit, &obj_fexit, &kfree_skb_fd);
+	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	for (i = 0; i < 6; i++) {
+		fentry_name[sizeof(fentry_name) - 2] = '1' + i;
+		prog[i] = bpf_object__find_program_by_title(obj_fentry, fentry_name);
+		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fentry_name))
+			goto close_prog;
+		link[i] = bpf_program__attach_trace(prog[i]);
+		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
+			goto close_prog;
+	}
+	data_map_fentry = bpf_object__find_map_by_name(obj_fentry, "fentry_t.bss");
+	if (CHECK(!data_map_fentry, "find_data_map", "data map not found\n"))
+		goto close_prog;
+
+	for (i = 6; i < 12; i++) {
+		fexit_name[sizeof(fexit_name) - 2] = '1' + i - 6;
+		prog[i] = bpf_object__find_program_by_title(obj_fexit, fexit_name);
+		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fexit_name))
+			goto close_prog;
+		link[i] = bpf_program__attach_trace(prog[i]);
+		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
+			goto close_prog;
+	}
+	data_map_fexit = bpf_object__find_map_by_name(obj_fexit, "fexit_te.bss");
+	if (CHECK(!data_map_fexit, "find_data_map", "data map not found\n"))
+		goto close_prog;
+
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "ipv6",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(data_map_fentry), &zero, &result);
+	if (CHECK(err, "get_result",
+		  "failed to get output data: %d\n", err))
+		goto close_prog;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(data_map_fexit), &zero, result + 6);
+	if (CHECK(err, "get_result",
+		  "failed to get output data: %d\n", err))
+		goto close_prog;
+
+	for (i = 0; i < 12; i++)
+		if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
+			  i % 6 + 1, result[i]))
+			goto close_prog;
+
+close_prog:
+	for (i = 0; i < 12; i++)
+		if (!IS_ERR_OR_NULL(link[i]))
+			bpf_link__destroy(link[i]);
+	bpf_object__close(obj_fentry);
+	bpf_object__close(obj_fexit);
+	bpf_object__close(pkt_obj);
+}
-- 
cgit v1.2.3


From e76d776e9ca1fe266b3a7f8091eee5d1e635a545 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:12 -0800
Subject: selftests/bpf: Add stress test for maximum number of progs

Add stress test for maximum number of attached BPF programs per BPF trampoline.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-13-ast@kernel.org
---
 .../selftests/bpf/prog_tests/fexit_stress.c        | 76 ++++++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fexit_stress.c

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
new file mode 100644
index 000000000000..3b9dbf7433f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+
+/* x86-64 fits 55 JITed and 43 interpreted progs into half page */
+#define CNT 40
+
+void test_fexit_stress(void)
+{
+	char test_skb[128] = {};
+	int fexit_fd[CNT] = {};
+	int link_fd[CNT] = {};
+	__u32 duration = 0;
+	char error[4096];
+	__u32 prog_ret;
+	int err, i, filter_fd;
+
+	const struct bpf_insn trace_program[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+
+	struct bpf_load_program_attr load_attr = {
+		.prog_type = BPF_PROG_TYPE_TRACING,
+		.license = "GPL",
+		.insns = trace_program,
+		.insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn),
+		.expected_attach_type = BPF_TRACE_FEXIT,
+	};
+
+	const struct bpf_insn skb_program[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+
+	struct bpf_load_program_attr skb_load_attr = {
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.license = "GPL",
+		.insns = skb_program,
+		.insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn),
+	};
+
+	err = libbpf_find_vmlinux_btf_id("bpf_fentry_test1",
+					 load_attr.expected_attach_type);
+	if (CHECK(err <= 0, "find_vmlinux_btf_id", "failed: %d\n", err))
+		goto out;
+	load_attr.attach_btf_id = err;
+
+	for (i = 0; i < CNT; i++) {
+		fexit_fd[i] = bpf_load_program_xattr(&load_attr, error, sizeof(error));
+		if (CHECK(fexit_fd[i] < 0, "fexit loaded",
+			  "failed: %d errno %d\n", fexit_fd[i], errno))
+			goto out;
+		link_fd[i] = bpf_raw_tracepoint_open(NULL, fexit_fd[i]);
+		if (CHECK(link_fd[i] < 0, "fexit attach failed",
+			  "prog %d failed: %d err %d\n", i, link_fd[i], errno))
+			goto out;
+	}
+
+	filter_fd = bpf_load_program_xattr(&skb_load_attr, error, sizeof(error));
+	if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n",
+		  filter_fd, errno))
+		goto out;
+
+	err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0,
+				0, &prog_ret, 0);
+	close(filter_fd);
+	CHECK_FAIL(err);
+out:
+	for (i = 0; i < CNT; i++) {
+		if (link_fd[i])
+			close(link_fd[i]);
+		if (fexit_fd[i])
+			close(fexit_fd[i]);
+	}
+}
-- 
cgit v1.2.3


From 9fd4a39dc7fe734d26eb89ea97e8c91331c6378c Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:13 -0800
Subject: bpf: Reserve space for BPF trampoline in BPF programs

BPF trampoline can be made to work with existing 5 bytes of BPF program
prologue, but let's add 5 bytes of NOPs to the beginning of every JITed BPF
program to make BPF trampoline job easier. They can be removed in the future.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-14-ast@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index be2b43a894f6..c06096df9118 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -206,7 +206,7 @@ struct jit_context {
 /* number of bytes emit_call() needs to generate call instruction */
 #define X86_CALL_SIZE		5
 
-#define PROLOGUE_SIZE		20
+#define PROLOGUE_SIZE		25
 
 /*
  * Emit x86-64 prologue code for BPF program and check its size.
@@ -215,8 +215,13 @@ struct jit_context {
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 {
 	u8 *prog = *pprog;
-	int cnt = 0;
+	int cnt = X86_CALL_SIZE;
 
+	/* BPF trampoline can be made to work without these nops,
+	 * but let's waste 5 bytes for now and optimize later
+	 */
+	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
+	prog += cnt;
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */
-- 
cgit v1.2.3


From 9cc31b3a092d9bf2a18f09ad77e727ddb42a5b1e Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:14 -0800
Subject: bpf: Fix race in btf_resolve_helper_id()

btf_resolve_helper_id() caching logic is a bit racy, since under root the
verifier can verify several programs in parallel. Fix it with READ/WRITE_ONCE.
Fix the type as well, since error is also recorded.

Fixes: a7658e1a4164 ("bpf: Check types of arguments passed into helpers")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-15-ast@kernel.org
---
 include/linux/bpf.h   |  5 +++--
 kernel/bpf/btf.c      | 26 +++++++++++++++++++++++++-
 kernel/bpf/verifier.c |  8 +++-----
 net/core/filter.c     |  2 +-
 4 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0d4c5c224d79..cb5a356381f5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -248,7 +248,7 @@ struct bpf_func_proto {
 		};
 		enum bpf_arg_type arg_type[5];
 	};
-	u32 *btf_id; /* BTF ids of arguments */
+	int *btf_id; /* BTF ids of arguments */
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -881,7 +881,8 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id);
-u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int);
+int btf_resolve_helper_id(struct bpf_verifier_log *log,
+			  const struct bpf_func_proto *fn, int);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 9e1164e5b429..033d071eb59c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3721,7 +3721,8 @@ again:
 	return -EINVAL;
 }
 
-u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg)
+static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn,
+				   int arg)
 {
 	char fnname[KSYM_SYMBOL_LEN + 4] = "btf_";
 	const struct btf_param *args;
@@ -3789,6 +3790,29 @@ u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg)
 	return btf_id;
 }
 
+int btf_resolve_helper_id(struct bpf_verifier_log *log,
+			  const struct bpf_func_proto *fn, int arg)
+{
+	int *btf_id = &fn->btf_id[arg];
+	int ret;
+
+	if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID)
+		return -EINVAL;
+
+	ret = READ_ONCE(*btf_id);
+	if (ret)
+		return ret;
+	/* ok to race the search. The result is the same */
+	ret = __btf_resolve_helper_id(log, fn->func, arg);
+	if (!ret) {
+		/* Function argument cannot be type 'void' */
+		bpf_log(log, "BTF resolution bug\n");
+		return -EFAULT;
+	}
+	WRITE_ONCE(*btf_id, ret);
+	return ret;
+}
+
 static int __get_type_size(struct btf *btf, u32 btf_id,
 			   const struct btf_type **bad_type)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8f89cfa93e88..e78ec7990767 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4147,11 +4147,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID) {
-			if (!fn->btf_id[i])
-				fn->btf_id[i] = btf_resolve_helper_id(&env->log, fn->func, i);
-			meta.btf_id = fn->btf_id[i];
-		}
+		err = btf_resolve_helper_id(&env->log, fn, i);
+		if (err > 0)
+			meta.btf_id = err;
 		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
 		if (err)
 			return err;
diff --git a/net/core/filter.c b/net/core/filter.c
index fc303abec8fa..f72face90659 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3816,7 +3816,7 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-static u32 bpf_skb_output_btf_ids[5];
+static int bpf_skb_output_btf_ids[5];
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
-- 
cgit v1.2.3


From 91cc1a99740e2ed1d903b5906afb470cc5a07379 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:15 -0800
Subject: bpf: Annotate context types

Annotate BPF program context types with program-side type and kernel-side type.
This type information is used by the verifier. btf_get_prog_ctx_type() is
used in the later patches to verify that BTF type of ctx in BPF program matches to
kernel expected ctx type. For example, the XDP program type is:
BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp, struct xdp_md, struct xdp_buff)
That means that XDP program should be written as:
int xdp_prog(struct xdp_md *ctx) { ... }

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-16-ast@kernel.org
---
 include/linux/bpf.h       |  11 ++++-
 include/linux/bpf_types.h |  78 ++++++++++++++++++++-----------
 kernel/bpf/btf.c          | 114 ++++++++++++++++++++++++++++++++++++++++++++--
 kernel/bpf/syscall.c      |   4 +-
 kernel/bpf/verifier.c     |   2 +-
 net/core/filter.c         |  10 ----
 6 files changed, 176 insertions(+), 43 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cb5a356381f5..9c48f11fe56e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -747,7 +747,7 @@ DECLARE_PER_CPU(int, bpf_prog_active);
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	extern const struct bpf_prog_ops _name ## _prog_ops; \
 	extern const struct bpf_verifier_ops _name ## _verifier_ops;
 #define BPF_MAP_TYPE(_id, _ops) \
@@ -1213,6 +1213,15 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 #endif
 
 #ifdef CONFIG_INET
+struct sk_reuseport_kern {
+	struct sk_buff *skb;
+	struct sock *sk;
+	struct sock *selected_sk;
+	void *data_end;
+	u32 hash;
+	u32 reuseport_id;
+	bool bind_inany;
+};
 bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 				  struct bpf_insn_access_aux *info);
 
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index de14872b01ba..93740b3614d7 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -2,42 +2,68 @@
 /* internal file - do not include directly */
 
 #ifdef CONFIG_NET
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act)
-BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp,
+	      struct xdp_md, struct xdp_buff)
 #ifdef CONFIG_CGROUP_BPF
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock,
+	      struct bpf_sock, struct sock)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr,
+	      struct bpf_sock_addr, struct bpf_sock_addr_kern)
 #endif
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
-BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops,
+	      struct bpf_sock_ops, struct bpf_sock_ops_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg,
+	      struct sk_msg_md, struct sk_msg)
+BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector,
+	      struct __sk_buff, struct bpf_flow_dissector)
 #endif
 #ifdef CONFIG_BPF_EVENTS
-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)
-BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
-BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
-BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing)
+BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe,
+	      bpf_user_pt_regs_t, struct pt_regs)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint,
+	      __u64, u64)
+BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event,
+	      struct bpf_perf_event_data, struct bpf_perf_event_data_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint,
+	      struct bpf_raw_tracepoint_args, u64)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable,
+	      struct bpf_raw_tracepoint_args, u64)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing,
+	      void *, void *)
 #endif
 #ifdef CONFIG_CGROUP_BPF
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev,
+	      struct bpf_cgroup_dev_ctx, struct bpf_cgroup_dev_ctx)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl,
+	      struct bpf_sysctl, struct bpf_sysctl_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt,
+	      struct bpf_sockopt, struct bpf_sockopt_kern)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
-BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
+	      __u32, u32)
 #endif
 #ifdef CONFIG_INET
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
+	      struct sk_reuseport_md, struct sk_reuseport_kern)
 #endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 033d071eb59c..4b7c8bd423d6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2,6 +2,8 @@
 /* Copyright (c) 2018 Facebook */
 
 #include <uapi/linux/btf.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/bpf_perf_event.h>
 #include <uapi/linux/types.h>
 #include <linux/seq_file.h>
 #include <linux/compiler.h>
@@ -16,6 +18,9 @@
 #include <linux/sort.h>
 #include <linux/bpf_verifier.h>
 #include <linux/btf.h>
+#include <linux/skmsg.h>
+#include <linux/perf_event.h>
+#include <net/sock.h>
 
 /* BTF (BPF Type Format) is the meta data format which describes
  * the data types of BPF program/map.  Hence, it basically focus
@@ -3439,13 +3444,98 @@ errout:
 
 extern char __weak _binary__btf_vmlinux_bin_start[];
 extern char __weak _binary__btf_vmlinux_bin_end[];
+extern struct btf *btf_vmlinux;
+
+#define BPF_MAP_TYPE(_id, _ops)
+static union {
+	struct bpf_ctx_convert {
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
+	prog_ctx_type _id##_prog; \
+	kern_ctx_type _id##_kern;
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+	} *__t;
+	/* 't' is written once under lock. Read many times. */
+	const struct btf_type *t;
+} bpf_ctx_convert;
+enum {
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
+	__ctx_convert##_id,
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+};
+static u8 bpf_ctx_convert_map[] = {
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
+	[_id] = __ctx_convert##_id,
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+};
+#undef BPF_MAP_TYPE
+
+static const struct btf_member *
+btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
+		      const struct btf_type *t, enum bpf_prog_type prog_type)
+{
+	const struct btf_type *conv_struct;
+	const struct btf_type *ctx_struct;
+	const struct btf_member *ctx_type;
+	const char *tname, *ctx_tname;
+
+	conv_struct = bpf_ctx_convert.t;
+	if (!conv_struct) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return NULL;
+	}
+	t = btf_type_by_id(btf, t->type);
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf, t->type);
+	if (!btf_type_is_struct(t)) {
+		/* Only pointer to struct is supported for now.
+		 * That means that BPF_PROG_TYPE_TRACEPOINT with BTF
+		 * is not supported yet.
+		 * BPF_PROG_TYPE_RAW_TRACEPOINT is fine.
+		 */
+		bpf_log(log, "BPF program ctx type is not a struct\n");
+		return NULL;
+	}
+	tname = btf_name_by_offset(btf, t->name_off);
+	if (!tname) {
+		bpf_log(log, "BPF program ctx struct doesn't have a name\n");
+		return NULL;
+	}
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
+	/* ctx_struct is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct __sk_buff'
+	 */
+	ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type);
+	if (!ctx_struct)
+		/* should not happen */
+		return NULL;
+	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off);
+	if (!ctx_tname) {
+		/* should not happen */
+		bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n");
+		return NULL;
+	}
+	/* only compare that prog's ctx type name is the same as
+	 * kernel expects. No need to compare field by field.
+	 * It's ok for bpf prog to do:
+	 * struct __sk_buff {};
+	 * int socket_filter_bpf_prog(struct __sk_buff *skb)
+	 * { // no fields of skb are ever used }
+	 */
+	if (strcmp(ctx_tname, tname))
+		return NULL;
+	return ctx_type;
+}
 
 struct btf *btf_parse_vmlinux(void)
 {
 	struct btf_verifier_env *env = NULL;
 	struct bpf_verifier_log *log;
 	struct btf *btf = NULL;
-	int err;
+	int err, i;
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
 	if (!env)
@@ -3479,6 +3569,26 @@ struct btf *btf_parse_vmlinux(void)
 	if (err)
 		goto errout;
 
+	/* find struct bpf_ctx_convert for type checking later */
+	for (i = 1; i <= btf->nr_types; i++) {
+		const struct btf_type *t;
+		const char *tname;
+
+		t = btf_type_by_id(btf, i);
+		if (!__btf_type_is_struct(t))
+			continue;
+		tname = __btf_name_by_offset(btf, t->name_off);
+		if (!strcmp(tname, "bpf_ctx_convert")) {
+			/* btf_parse_vmlinux() runs under bpf_verifier_lock */
+			bpf_ctx_convert.t = t;
+			break;
+		}
+	}
+	if (i > btf->nr_types) {
+		err = -ENOENT;
+		goto errout;
+	}
+
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
 	return btf;
@@ -3492,8 +3602,6 @@ errout:
 	return ERR_PTR(err);
 }
 
-extern struct btf *btf_vmlinux;
-
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e2e37bea86bc..05a0ee75eca0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -43,7 +43,7 @@ static DEFINE_SPINLOCK(map_idr_lock);
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
 static const struct bpf_map_ops * const bpf_map_types[] = {
-#define BPF_PROG_TYPE(_id, _ops)
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
 #define BPF_MAP_TYPE(_id, _ops) \
 	[_id] = &_ops,
 #include <linux/bpf_types.h>
@@ -1189,7 +1189,7 @@ err_put:
 }
 
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _prog_ops,
 #define BPF_MAP_TYPE(_id, _ops)
 #include <linux/bpf_types.h>
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e78ec7990767..7395d6bebefd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -23,7 +23,7 @@
 #include "disasm.h"
 
 static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _verifier_ops,
 #define BPF_MAP_TYPE(_id, _ops)
 #include <linux/bpf_types.h>
diff --git a/net/core/filter.c b/net/core/filter.c
index f72face90659..49ded4a7588a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8684,16 +8684,6 @@ out:
 }
 
 #ifdef CONFIG_INET
-struct sk_reuseport_kern {
-	struct sk_buff *skb;
-	struct sock *sk;
-	struct sock *selected_sk;
-	void *data_end;
-	u32 hash;
-	u32 reuseport_id;
-	bool bind_inany;
-};
-
 static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 				    struct sock_reuseport *reuse,
 				    struct sock *sk, struct sk_buff *skb,
-- 
cgit v1.2.3


From 8c1b6e69dcc1e11bd24111e3734dd740aaf3fda1 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:16 -0800
Subject: bpf: Compare BTF types of functions arguments with actual types

Make the verifier check that BTF types of function arguments match actual types
passed into top-level BPF program and into BPF-to-BPF calls. If types match
such BPF programs and sub-programs will have full support of BPF trampoline. If
types mismatch the trampoline has to be conservative. It has to save/restore
five program arguments and assume 64-bit scalars.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-17-ast@kernel.org
---
 include/linux/bpf.h          |  8 +++++
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/btf.c             | 82 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c         |  1 +
 kernel/bpf/verifier.c        | 18 ++++++++--
 5 files changed, 107 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9c48f11fe56e..c70bf04726b4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -480,6 +480,10 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #endif
 
+struct bpf_func_info_aux {
+	bool unreliable;
+};
+
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
@@ -494,6 +498,7 @@ struct bpf_prog_aux {
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool func_proto_unreliable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
@@ -518,6 +523,7 @@ struct bpf_prog_aux {
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
+	struct bpf_func_info_aux *func_info_aux;
 	/* bpf_line_info loaded from userspace.  linfo->insn_off
 	 * has the xlated insn offset.
 	 * Both the main and sub prog share the same linfo.
@@ -890,6 +896,8 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   const char *func_name,
 			   struct btf_func_model *m);
 
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6e7284ea1468..cdd08bf0ec06 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -343,6 +343,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 #define BPF_MAX_SUBPROGS 256
 
 struct bpf_subprog_info {
+	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4b7c8bd423d6..4620267b186e 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3985,6 +3985,88 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 	return 0;
 }
 
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_verifier_state *st = env->cur_state;
+	struct bpf_func_state *func = st->frame[st->curframe];
+	struct bpf_reg_state *reg = func->regs;
+	struct bpf_verifier_log *log = &env->log;
+	struct bpf_prog *prog = env->prog;
+	struct btf *btf = prog->aux->btf;
+	const struct btf_param *args;
+	const struct btf_type *t;
+	u32 i, nargs, btf_id;
+	const char *tname;
+
+	if (!prog->aux->func_info)
+		return 0;
+
+	btf_id = prog->aux->func_info[subprog].type_id;
+	if (!btf_id)
+		return 0;
+
+	if (prog->aux->func_info_aux[subprog].unreliable)
+		return 0;
+
+	t = btf_type_by_id(btf, btf_id);
+	if (!t || !btf_type_is_func(t)) {
+		bpf_log(log, "BTF of subprog %d doesn't point to KIND_FUNC\n",
+			subprog);
+		return -EINVAL;
+	}
+	tname = btf_name_by_offset(btf, t->name_off);
+
+	t = btf_type_by_id(btf, t->type);
+	if (!t || !btf_type_is_func_proto(t)) {
+		bpf_log(log, "Invalid type of func %s\n", tname);
+		return -EINVAL;
+	}
+	args = (const struct btf_param *)(t + 1);
+	nargs = btf_type_vlen(t);
+	if (nargs > 5) {
+		bpf_log(log, "Function %s has %d > 5 args\n", tname, nargs);
+		goto out;
+	}
+	/* check that BTF function arguments match actual types that the
+	 * verifier sees.
+	 */
+	for (i = 0; i < nargs; i++) {
+		t = btf_type_by_id(btf, args[i].type);
+		while (btf_type_is_modifier(t))
+			t = btf_type_by_id(btf, t->type);
+		if (btf_type_is_int(t) || btf_type_is_enum(t)) {
+			if (reg[i + 1].type == SCALAR_VALUE)
+				continue;
+			bpf_log(log, "R%d is not a scalar\n", i + 1);
+			goto out;
+		}
+		if (btf_type_is_ptr(t)) {
+			if (reg[i + 1].type == SCALAR_VALUE) {
+				bpf_log(log, "R%d is not a pointer\n", i + 1);
+				goto out;
+			}
+			/* If program is passing PTR_TO_CTX into subprogram
+			 * check that BTF type matches.
+			 */
+			if (reg[i + 1].type == PTR_TO_CTX &&
+			    !btf_get_prog_ctx_type(log, btf, t, prog->type))
+				goto out;
+			/* All other pointers are ok */
+			continue;
+		}
+		bpf_log(log, "Unrecognized argument type %s\n",
+			btf_kind_str[BTF_INFO_KIND(t->info)]);
+		goto out;
+	}
+	return 0;
+out:
+	/* LLVM optimizations can remove arguments from static functions. */
+	bpf_log(log,
+		"Type info disagrees with actual arguments due to compiler optimizations\n");
+	prog->aux->func_info_aux[subprog].unreliable = true;
+	return 0;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 05a0ee75eca0..43ba647de720 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1328,6 +1328,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
 	kvfree(aux->func_info);
+	kfree(aux->func_info_aux);
 	free_used_maps(aux);
 	bpf_prog_uncharge_memlock(aux->prog);
 	security_bpf_prog_free(aux);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7395d6bebefd..11910149ca2f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3970,6 +3970,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* only increment it after check_reg_arg() finished */
 	state->curframe++;
 
+	if (btf_check_func_arg_match(env, subprog))
+		return -EINVAL;
+
 	/* and go analyze first insn of the callee */
 	*insn_idx = target_insn;
 
@@ -6564,6 +6567,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
+	struct bpf_func_info_aux *info_aux = NULL;
 	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
@@ -6597,6 +6601,9 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!krecord)
 		return -ENOMEM;
+	info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+	if (!info_aux)
+		goto err_free;
 
 	for (i = 0; i < nfuncs; i++) {
 		ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
@@ -6648,29 +6655,31 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			ret = -EINVAL;
 			goto err_free;
 		}
-
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
 
 	prog->aux->func_info = krecord;
 	prog->aux->func_info_cnt = nfuncs;
+	prog->aux->func_info_aux = info_aux;
 	return 0;
 
 err_free:
 	kvfree(krecord);
+	kfree(info_aux);
 	return ret;
 }
 
 static void adjust_btf_func(struct bpf_verifier_env *env)
 {
+	struct bpf_prog_aux *aux = env->prog->aux;
 	int i;
 
-	if (!env->prog->aux->func_info)
+	if (!aux->func_info)
 		return;
 
 	for (i = 0; i < env->subprog_cnt; i++)
-		env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start;
+		aux->func_info[i].insn_off = env->subprog_info[i].start;
 }
 
 #define MIN_BPF_LINEINFO_SIZE	(offsetof(struct bpf_line_info, line_col) + \
@@ -7651,6 +7660,9 @@ static int do_check(struct bpf_verifier_env *env)
 			0 /* frameno */,
 			0 /* subprogno, zero == main subprog */);
 
+	if (btf_check_func_arg_match(env, 0))
+		return -EINVAL;
+
 	for (;;) {
 		struct bpf_insn *insn;
 		u8 class;
-- 
cgit v1.2.3


From 5b92a28aae4dd0f88778d540ecfdcdaec5a41723 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:17 -0800
Subject: bpf: Support attaching tracing BPF program to other BPF programs

Allow FENTRY/FEXIT BPF programs to attach to other BPF programs of any type
including their subprograms. This feature allows snooping on input and output
packets in XDP, TC programs including their return values. In order to do that
the verifier needs to track types not only of vmlinux, but types of other BPF
programs as well. The verifier also needs to translate uapi/linux/bpf.h types
used by networking programs into kernel internal BTF types used by FENTRY/FEXIT
BPF programs. In some cases LLVM optimizations can remove arguments from BPF
subprograms without adjusting BTF info that LLVM backend knows. When BTF info
disagrees with actual types that the verifiers sees the BPF trampoline has to
fallback to conservative and treat all arguments as u64. The FENTRY/FEXIT
program can still attach to such subprograms, but it won't be able to recognize
pointer types like 'struct sk_buff *' and it won't be able to pass them to
bpf_skb_output() for dumping packets to user space. The FENTRY/FEXIT program
would need to use bpf_probe_read_kernel() instead.

The BPF_PROG_LOAD command is extended with attach_prog_fd field. When it's set
to zero the attach_btf_id is one vmlinux BTF type ids. When attach_prog_fd
points to previously loaded BPF program the attach_btf_id is BTF type id of
main function or one of its subprograms.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-18-ast@kernel.org
---
 arch/x86/net/bpf_jit_comp.c |  3 +-
 include/linux/bpf.h         |  1 +
 include/linux/btf.h         |  1 +
 include/uapi/linux/bpf.h    |  1 +
 kernel/bpf/btf.c            | 70 +++++++++++++++++++++++++++++++++-----
 kernel/bpf/core.c           |  2 ++
 kernel/bpf/syscall.c        | 19 ++++++++---
 kernel/bpf/verifier.c       | 83 +++++++++++++++++++++++++++++++++++++--------
 8 files changed, 152 insertions(+), 28 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index c06096df9118..2e586f579945 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -504,7 +504,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	u8 *prog;
 	int ret;
 
-	if (!is_kernel_text((long)ip))
+	if (!is_kernel_text((long)ip) &&
+	    !is_bpf_text_address((long)ip))
 		/* BPF trampoline in modules is not supported */
 		return -EINVAL;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c70bf04726b4..5b81cde47314 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -495,6 +495,7 @@ struct bpf_prog_aux {
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+	struct bpf_prog *linked_prog;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 9dee00859c5f..79d4abc2556a 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -88,6 +88,7 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
+struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 69c200e6e696..4842a134b202 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -425,6 +425,7 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
+		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4620267b186e..40efde5eedcb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3530,6 +3530,20 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
 	return ctx_type;
 }
 
+static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
+				     struct btf *btf,
+				     const struct btf_type *t,
+				     enum bpf_prog_type prog_type)
+{
+	const struct btf_member *prog_ctx_type, *kern_ctx_type;
+
+	prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type);
+	if (!prog_ctx_type)
+		return -ENOENT;
+	kern_ctx_type = prog_ctx_type + 1;
+	return kern_ctx_type->type;
+}
+
 struct btf *btf_parse_vmlinux(void)
 {
 	struct btf_verifier_env *env = NULL;
@@ -3602,15 +3616,29 @@ errout:
 	return ERR_PTR(err);
 }
 
+struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
+{
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+
+	if (tgt_prog) {
+		return tgt_prog->aux->btf;
+	} else {
+		return btf_vmlinux;
+	}
+}
+
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
 {
 	const struct btf_type *t = prog->aux->attach_func_proto;
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct btf *btf = bpf_prog_get_target_btf(prog);
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
 	const struct btf_param *args;
 	u32 nr_args, arg;
+	int ret;
 
 	if (off % 8) {
 		bpf_log(log, "func '%s' offset %d is not multiple of 8\n",
@@ -3619,7 +3647,8 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	}
 	arg = off / 8;
 	args = (const struct btf_param *)(t + 1);
-	nr_args = btf_type_vlen(t);
+	/* if (t == NULL) Fall back to default BPF prog with 5 u64 arguments */
+	nr_args = t ? btf_type_vlen(t) : 5;
 	if (prog->aux->attach_btf_trace) {
 		/* skip first 'void *__data' argument in btf_trace_##name typedef */
 		args++;
@@ -3628,18 +3657,24 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 
 	if (prog->expected_attach_type == BPF_TRACE_FEXIT &&
 	    arg == nr_args) {
+		if (!t)
+			/* Default prog with 5 args. 6th arg is retval. */
+			return true;
 		/* function return type */
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 	} else if (arg >= nr_args) {
 		bpf_log(log, "func '%s' doesn't have %d-th argument\n",
 			tname, arg + 1);
 		return false;
 	} else {
-		t = btf_type_by_id(btf_vmlinux, args[arg].type);
+		if (!t)
+			/* Default prog with 5 args */
+			return true;
+		t = btf_type_by_id(btf, args[arg].type);
 	}
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 	if (btf_type_is_int(t))
 		/* accessing a scalar */
 		return true;
@@ -3647,7 +3682,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		bpf_log(log,
 			"func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n",
 			tname, arg,
-			__btf_name_by_offset(btf_vmlinux, t->name_off),
+			__btf_name_by_offset(btf, t->name_off),
 			btf_kind_str[BTF_INFO_KIND(t->info)]);
 		return false;
 	}
@@ -3662,10 +3697,19 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	info->reg_type = PTR_TO_BTF_ID;
 	info->btf_id = t->type;
 
-	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (tgt_prog) {
+		ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type);
+		if (ret > 0) {
+			info->btf_id = ret;
+			return true;
+		} else {
+			return false;
+		}
+	}
+	t = btf_type_by_id(btf, t->type);
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 	if (!btf_type_is_struct(t)) {
 		bpf_log(log,
 			"func '%s' arg%d type %s is not a struct\n",
@@ -3674,7 +3718,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	}
 	bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n",
 		tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)],
-		__btf_name_by_offset(btf_vmlinux, t->name_off));
+		__btf_name_by_offset(btf, t->name_off));
 	return true;
 }
 
@@ -3954,6 +3998,16 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 	u32 i, nargs;
 	int ret;
 
+	if (!func) {
+		/* BTF function prototype doesn't match the verifier types.
+		 * Fall back to 5 u64 args.
+		 */
+		for (i = 0; i < 5; i++)
+			m->arg_size[i] = 8;
+		m->ret_size = 8;
+		m->nr_args = 5;
+		return 0;
+	}
 	args = (const struct btf_param *)(func + 1);
 	nargs = btf_type_vlen(func);
 	if (nargs >= MAX_BPF_FUNC_ARGS) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index da5a8b8e278f..b5945c3aaa8e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2031,6 +2031,8 @@ void bpf_prog_free(struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
 
+	if (aux->linked_prog)
+		bpf_prog_put(aux->linked_prog);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 43ba647de720..c88c815c2154 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1577,7 +1577,7 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 static int
 bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			   enum bpf_attach_type expected_attach_type,
-			   u32 btf_id)
+			   u32 btf_id, u32 prog_fd)
 {
 	switch (prog_type) {
 	case BPF_PROG_TYPE_TRACING:
@@ -1585,7 +1585,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			return -EINVAL;
 		break;
 	default:
-		if (btf_id)
+		if (btf_id || prog_fd)
 			return -EINVAL;
 		break;
 	}
@@ -1636,7 +1636,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD attach_btf_id
+#define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
 
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
@@ -1679,7 +1679,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
-				       attr->attach_btf_id))
+				       attr->attach_btf_id,
+				       attr->attach_prog_fd))
 		return -EINVAL;
 
 	/* plain bpf_prog allocation */
@@ -1689,6 +1690,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
+	if (attr->attach_prog_fd) {
+		struct bpf_prog *tgt_prog;
+
+		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			goto free_prog_nouncharge;
+		}
+		prog->aux->linked_prog = tgt_prog;
+	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 11910149ca2f..e9dc95a18d44 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9390,13 +9390,17 @@ static void print_verification_stats(struct bpf_verifier_env *env)
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
+	int ret = 0, subprog = -1, i;
 	struct bpf_trampoline *tr;
 	const struct btf_type *t;
+	bool conservative = true;
 	const char *tname;
-	int ret = 0;
+	struct btf *btf;
 	long addr;
+	u64 key;
 
 	if (prog->type != BPF_PROG_TYPE_TRACING)
 		return 0;
@@ -9405,19 +9409,47 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		verbose(env, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
-	t = btf_type_by_id(btf_vmlinux, btf_id);
+	btf = bpf_prog_get_target_btf(prog);
+	if (!btf) {
+		verbose(env,
+			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
+		return -EINVAL;
+	}
+	t = btf_type_by_id(btf, btf_id);
 	if (!t) {
 		verbose(env, "attach_btf_id %u is invalid\n", btf_id);
 		return -EINVAL;
 	}
-	tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+	tname = btf_name_by_offset(btf, t->name_off);
 	if (!tname) {
 		verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
 		return -EINVAL;
 	}
+	if (tgt_prog) {
+		struct bpf_prog_aux *aux = tgt_prog->aux;
+
+		for (i = 0; i < aux->func_info_cnt; i++)
+			if (aux->func_info[i].type_id == btf_id) {
+				subprog = i;
+				break;
+			}
+		if (subprog == -1) {
+			verbose(env, "Subprog %s doesn't exist\n", tname);
+			return -EINVAL;
+		}
+		conservative = aux->func_info_aux[subprog].unreliable;
+		key = ((u64)aux->id) << 32 | btf_id;
+	} else {
+		key = btf_id;
+	}
 
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_RAW_TP:
+		if (tgt_prog) {
+			verbose(env,
+				"Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
+			return -EINVAL;
+		}
 		if (!btf_type_is_typedef(t)) {
 			verbose(env, "attach_btf_id %u is not a typedef\n",
 				btf_id);
@@ -9429,11 +9461,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			return -EINVAL;
 		}
 		tname += sizeof(prefix) - 1;
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_ptr(t))
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
@@ -9452,30 +9484,51 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				btf_id);
 			return -EINVAL;
 		}
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		tr = bpf_trampoline_lookup(btf_id);
+		tr = bpf_trampoline_lookup(key);
 		if (!tr)
 			return -ENOMEM;
 		prog->aux->attach_func_name = tname;
+		/* t is either vmlinux type or another program's type */
 		prog->aux->attach_func_proto = t;
 		mutex_lock(&tr->mutex);
 		if (tr->func.addr) {
 			prog->aux->trampoline = tr;
 			goto out;
 		}
-		ret = btf_distill_func_proto(&env->log, btf_vmlinux, t,
+		if (tgt_prog && conservative) {
+			prog->aux->attach_func_proto = NULL;
+			t = NULL;
+		}
+		ret = btf_distill_func_proto(&env->log, btf, t,
 					     tname, &tr->func.model);
 		if (ret < 0)
 			goto out;
-		addr = kallsyms_lookup_name(tname);
-		if (!addr) {
-			verbose(env,
-				"The address of function %s cannot be found\n",
-				tname);
-			ret = -ENOENT;
-			goto out;
+		if (tgt_prog) {
+			if (!tgt_prog->jited) {
+				/* for now */
+				verbose(env, "Can trace only JITed BPF progs\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (tgt_prog->type == BPF_PROG_TYPE_TRACING) {
+				/* prevent cycles */
+				verbose(env, "Cannot recursively attach\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
+		} else {
+			addr = kallsyms_lookup_name(tname);
+			if (!addr) {
+				verbose(env,
+					"The address of function %s cannot be found\n",
+					tname);
+				ret = -ENOENT;
+				goto out;
+			}
 		}
 		tr->func.addr = (void *)addr;
 		prog->aux->trampoline = tr;
-- 
cgit v1.2.3


From e7bf94dbb882b7d679a6a18e40e4f28076eb249f Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:18 -0800
Subject: libbpf: Add support for attaching BPF programs to other BPF programs

Extend libbpf api to pass attach_prog_fd into bpf_object__open.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-19-ast@kernel.org
---
 tools/include/uapi/linux/bpf.h |  1 +
 tools/lib/bpf/bpf.c            |  8 +++--
 tools/lib/bpf/bpf.h            |  5 ++-
 tools/lib/bpf/libbpf.c         | 71 +++++++++++++++++++++++++++++++++++-------
 tools/lib/bpf/libbpf.h         |  3 +-
 5 files changed, 71 insertions(+), 17 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 69c200e6e696..4842a134b202 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -425,6 +425,7 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
+		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index b3e3e99a0f28..98596e15390f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -228,10 +228,13 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
-	if (attr.prog_type == BPF_PROG_TYPE_TRACING)
+	if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
 		attr.attach_btf_id = load_attr->attach_btf_id;
-	else
+		attr.attach_prog_fd = load_attr->attach_prog_fd;
+	} else {
 		attr.prog_ifindex = load_attr->prog_ifindex;
+		attr.kern_version = load_attr->kern_version;
+	}
 	attr.insn_cnt = (__u32)load_attr->insns_cnt;
 	attr.insns = ptr_to_u64(load_attr->insns);
 	attr.license = ptr_to_u64(load_attr->license);
@@ -245,7 +248,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		attr.log_size = 0;
 	}
 
-	attr.kern_version = load_attr->kern_version;
 	attr.prog_btf_fd = load_attr->prog_btf_fd;
 	attr.func_info_rec_size = load_attr->func_info_rec_size;
 	attr.func_info_cnt = load_attr->func_info_cnt;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 1c53bc5b4b3c..3c791fa8e68e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -77,7 +77,10 @@ struct bpf_load_program_attr {
 	const struct bpf_insn *insns;
 	size_t insns_cnt;
 	const char *license;
-	__u32 kern_version;
+	union {
+		__u32 kern_version;
+		__u32 attach_prog_fd;
+	};
 	union {
 		__u32 prog_ifindex;
 		__u32 attach_btf_id;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 98ee033e021f..7132c6bdec02 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -189,6 +189,7 @@ struct bpf_program {
 
 	enum bpf_attach_type expected_attach_type;
 	__u32 attach_btf_id;
+	__u32 attach_prog_fd;
 	void *func_info;
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
@@ -3683,8 +3684,13 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
-	load_attr.kern_version = kern_version;
-	load_attr.prog_ifindex = prog->prog_ifindex;
+	if (prog->type == BPF_PROG_TYPE_TRACING) {
+		load_attr.attach_prog_fd = prog->attach_prog_fd;
+		load_attr.attach_btf_id = prog->attach_btf_id;
+	} else {
+		load_attr.kern_version = kern_version;
+		load_attr.prog_ifindex = prog->prog_ifindex;
+	}
 	/* if .BTF.ext was loaded, kernel supports associated BTF for prog */
 	if (prog->obj->btf_ext)
 		btf_fd = bpf_object__btf_fd(prog->obj);
@@ -3699,7 +3705,6 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.line_info_cnt = prog->line_info_cnt;
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
-	load_attr.attach_btf_id = prog->attach_btf_id;
 
 retry_load:
 	log_buf = malloc(log_buf_size);
@@ -3856,9 +3861,9 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
-static int libbpf_attach_btf_id_by_name(const char *name,
-					enum bpf_attach_type attach_type);
-
+static int libbpf_find_attach_btf_id(const char *name,
+				     enum bpf_attach_type attach_type,
+				     __u32 attach_prog_fd);
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		   struct bpf_object_open_opts *opts)
@@ -3869,6 +3874,7 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	const char *obj_name;
 	char tmp_name[64];
 	bool relaxed_maps;
+	__u32 attach_prog_fd;
 	int err;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
@@ -3899,6 +3905,7 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false);
 	relaxed_maps = OPTS_GET(opts, relaxed_maps, false);
 	pin_root_path = OPTS_GET(opts, pin_root_path, NULL);
+	attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
 
 	CHECK_ERR(bpf_object__elf_init(obj), err, out);
 	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
@@ -3923,11 +3930,13 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		bpf_program__set_type(prog, prog_type);
 		bpf_program__set_expected_attach_type(prog, attach_type);
 		if (prog_type == BPF_PROG_TYPE_TRACING) {
-			err = libbpf_attach_btf_id_by_name(prog->section_name,
-							   attach_type);
+			err = libbpf_find_attach_btf_id(prog->section_name,
+							attach_type,
+							attach_prog_fd);
 			if (err <= 0)
 				goto out;
 			prog->attach_btf_id = err;
+			prog->attach_prog_fd = attach_prog_fd;
 		}
 	}
 
@@ -5086,8 +5095,42 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 	return err;
 }
 
-static int libbpf_attach_btf_id_by_name(const char *name,
-					enum bpf_attach_type attach_type)
+static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info *info;
+	struct btf *btf = NULL;
+	int err = -EINVAL;
+
+	info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		pr_warn("failed get_prog_info_linear for FD %d\n",
+			attach_prog_fd);
+		return -EINVAL;
+	}
+	info = &info_linear->info;
+	if (!info->btf_id) {
+		pr_warn("The target program doesn't have BTF\n");
+		goto out;
+	}
+	if (btf__get_from_id(info->btf_id, &btf)) {
+		pr_warn("Failed to get BTF of the program\n");
+		goto out;
+	}
+	err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+	btf__free(btf);
+	if (err <= 0) {
+		pr_warn("%s is not found in prog's BTF\n", name);
+		goto out;
+	}
+out:
+	free(info_linear);
+	return err;
+}
+
+static int libbpf_find_attach_btf_id(const char *name,
+				     enum bpf_attach_type attach_type,
+				     __u32 attach_prog_fd)
 {
 	int i, err;
 
@@ -5099,8 +5142,12 @@ static int libbpf_attach_btf_id_by_name(const char *name,
 			continue;
 		if (strncmp(name, section_names[i].sec, section_names[i].len))
 			continue;
-		err = libbpf_find_vmlinux_btf_id(name + section_names[i].len,
-						 attach_type);
+		if (attach_prog_fd)
+			err = libbpf_find_prog_btf_id(name + section_names[i].len,
+						      attach_prog_fd);
+		else
+			err = libbpf_find_vmlinux_btf_id(name + section_names[i].len,
+							 attach_type);
 		if (err <= 0)
 			pr_warn("%s is not found in vmlinux BTF\n", name);
 		return err;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index fbff419f6daf..0dbf4bfba0c4 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -108,8 +108,9 @@ struct bpf_object_open_opts {
 	 * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
 	 */
 	const char *pin_root_path;
+	__u32 attach_prog_fd;
 };
-#define bpf_object_open_opts__last_field pin_root_path
+#define bpf_object_open_opts__last_field attach_prog_fd
 
 LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
 LIBBPF_API struct bpf_object *
-- 
cgit v1.2.3


From 4c0963243c5f56bffe8eaba6acc5b076d51797f4 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:19 -0800
Subject: selftests/bpf: Extend test_pkt_access test

The test_pkt_access.o is used by multiple tests. Fix its section name so that
program type can be automatically detected by libbpf and make it call other
subprograms with skb argument.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-20-ast@kernel.org
---
 .../testing/selftests/bpf/progs/test_pkt_access.c  | 38 ++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 7cf42d14103f..3a7b4b607ed3 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
@@ -17,8 +17,38 @@
 #define barrier() __asm__ __volatile__("": : :"memory")
 int _version SEC("version") = 1;
 
-SEC("test1")
-int process(struct __sk_buff *skb)
+/* llvm will optimize both subprograms into exactly the same BPF assembly
+ *
+ * Disassembly of section .text:
+ *
+ * 0000000000000000 test_pkt_access_subprog1:
+ * ; 	return skb->len * 2;
+ *        0:	61 10 00 00 00 00 00 00	r0 = *(u32 *)(r1 + 0)
+ *        1:	64 00 00 00 01 00 00 00	w0 <<= 1
+ *        2:	95 00 00 00 00 00 00 00	exit
+ *
+ * 0000000000000018 test_pkt_access_subprog2:
+ * ; 	return skb->len * val;
+ *        3:	61 10 00 00 00 00 00 00	r0 = *(u32 *)(r1 + 0)
+ *        4:	64 00 00 00 01 00 00 00	w0 <<= 1
+ *        5:	95 00 00 00 00 00 00 00	exit
+ *
+ * Which makes it an interesting test for BTF-enabled verifier.
+ */
+static __attribute__ ((noinline))
+int test_pkt_access_subprog1(volatile struct __sk_buff *skb)
+{
+	return skb->len * 2;
+}
+
+static __attribute__ ((noinline))
+int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb)
+{
+	return skb->len * val;
+}
+
+SEC("classifier/test_pkt_access")
+int test_pkt_access(struct __sk_buff *skb)
 {
 	void *data_end = (void *)(long)skb->data_end;
 	void *data = (void *)(long)skb->data;
@@ -48,6 +78,10 @@ int process(struct __sk_buff *skb)
 		tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len);
 	}
 
+	if (test_pkt_access_subprog1(skb) != skb->len * 2)
+		return TC_ACT_SHOT;
+	if (test_pkt_access_subprog2(2, skb) != skb->len * 2)
+		return TC_ACT_SHOT;
 	if (tcp) {
 		if (((void *)(tcp) + 20) > data_end || proto != 6)
 			return TC_ACT_SHOT;
-- 
cgit v1.2.3


From d6f39601ec5e708fb666a2ad437c7bef4cfab39b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 14 Nov 2019 10:57:20 -0800
Subject: selftests/bpf: Add a test for attaching BPF prog to another BPF prog
 and subprog

Add a test that attaches one FEXIT program to main sched_cls networking program
and two other FEXIT programs to subprograms. All three tracing programs
access return values and skb->len of networking program and subprograms.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-21-ast@kernel.org
---
 .../selftests/bpf/prog_tests/fexit_bpf2bpf.c       | 76 ++++++++++++++++++
 tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c  | 91 ++++++++++++++++++++++
 2 files changed, 167 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
 create mode 100644 tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
new file mode 100644
index 000000000000..15c7378362dd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+
+#define PROG_CNT 3
+
+void test_fexit_bpf2bpf(void)
+{
+	const char *prog_name[PROG_CNT] = {
+		"fexit/test_pkt_access",
+		"fexit/test_pkt_access_subprog1",
+		"fexit/test_pkt_access_subprog2",
+	};
+	struct bpf_object *obj = NULL, *pkt_obj;
+	int err, pkt_fd, i;
+	struct bpf_link *link[PROG_CNT] = {};
+	struct bpf_program *prog[PROG_CNT];
+	__u32 duration, retval;
+	struct bpf_map *data_map;
+	const int zero = 0;
+	u64 result[PROG_CNT];
+
+	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_UNSPEC,
+			    &pkt_obj, &pkt_fd);
+	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+		return;
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
+			    .attach_prog_fd = pkt_fd,
+			   );
+
+	obj = bpf_object__open_file("./fexit_bpf2bpf.o", &opts);
+	if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
+		  "failed to open fexit_bpf2bpf: %ld\n",
+		  PTR_ERR(obj)))
+		goto close_prog;
+
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "err %d\n", err))
+		goto close_prog;
+
+	for (i = 0; i < PROG_CNT; i++) {
+		prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]);
+		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name[i]))
+			goto close_prog;
+		link[i] = bpf_program__attach_trace(prog[i]);
+		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
+			goto close_prog;
+	}
+	data_map = bpf_object__find_map_by_name(obj, "fexit_bp.bss");
+	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
+		goto close_prog;
+
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "ipv6",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result);
+	if (CHECK(err, "get_result",
+		  "failed to get output data: %d\n", err))
+		goto close_prog;
+
+	for (i = 0; i < PROG_CNT; i++)
+		if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n",
+			  result[i]))
+			goto close_prog;
+
+close_prog:
+	for (i = 0; i < PROG_CNT; i++)
+		if (!IS_ERR_OR_NULL(link[i]))
+			bpf_link__destroy(link[i]);
+	if (!IS_ERR_OR_NULL(obj))
+		bpf_object__close(obj);
+	bpf_object__close(pkt_obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
new file mode 100644
index 000000000000..981f0474da5a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct sk_buff {
+	unsigned int len;
+};
+
+struct args {
+	struct sk_buff *skb;
+	ks32 ret;
+};
+static volatile __u64 test_result;
+SEC("fexit/test_pkt_access")
+int test_main(struct args *ctx)
+{
+	struct sk_buff *skb = ctx->skb;
+	int len;
+
+	__builtin_preserve_access_index(({
+		len = skb->len;
+	}));
+	if (len != 74 || ctx->ret != 0)
+		return 0;
+	test_result = 1;
+	return 0;
+}
+
+struct args_subprog1 {
+	struct sk_buff *skb;
+	ks32 ret;
+};
+static volatile __u64 test_result_subprog1;
+SEC("fexit/test_pkt_access_subprog1")
+int test_subprog1(struct args_subprog1 *ctx)
+{
+	struct sk_buff *skb = ctx->skb;
+	int len;
+
+	__builtin_preserve_access_index(({
+		len = skb->len;
+	}));
+	if (len != 74 || ctx->ret != 148)
+		return 0;
+	test_result_subprog1 = 1;
+	return 0;
+}
+
+/* Though test_pkt_access_subprog2() is defined in C as:
+ * static __attribute__ ((noinline))
+ * int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb)
+ * {
+ *     return skb->len * val;
+ * }
+ * llvm optimizations remove 'int val' argument and generate BPF assembly:
+ *   r0 = *(u32 *)(r1 + 0)
+ *   w0 <<= 1
+ *   exit
+ * In such case the verifier falls back to conservative and
+ * tracing program can access arguments and return value as u64
+ * instead of accurate types.
+ */
+struct args_subprog2 {
+	ku64 args[5];
+	ku64 ret;
+};
+static volatile __u64 test_result_subprog2;
+SEC("fexit/test_pkt_access_subprog2")
+int test_subprog2(struct args_subprog2 *ctx)
+{
+	struct sk_buff *skb = (void *)ctx->args[0];
+	__u64 ret;
+	int len;
+
+	bpf_probe_read_kernel(&len, sizeof(len),
+			      __builtin_preserve_access_index(&skb->len));
+
+	ret = ctx->ret;
+	/* bpf_prog_load() loads "test_pkt_access.o" with BPF_F_TEST_RND_HI32
+	 * which randomizes upper 32 bits after BPF_ALU32 insns.
+	 * Hence after 'w0 <<= 1' upper bits of $rax are random.
+	 * That is expected and correct. Trim them.
+	 */
+	ret = (__u32) ret;
+	if (len != 74 || ret != 148)
+		return 0;
+	test_result_subprog2 = 1;
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 1e0bd5a091e5d9e0f1d5b0e6329b87bb1792f784 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Sun, 17 Nov 2019 09:28:02 -0800
Subject: bpf: Switch bpf_map ref counter to atomic64_t so bpf_map_inc() never
 fails

92117d8443bc ("bpf: fix refcnt overflow") turned refcounting of bpf_map into
potentially failing operation, when refcount reaches BPF_MAX_REFCNT limit
(32k). Due to using 32-bit counter, it's possible in practice to overflow
refcounter and make it wrap around to 0, causing erroneous map free, while
there are still references to it, causing use-after-free problems.

But having a failing refcounting operations are problematic in some cases. One
example is mmap() interface. After establishing initial memory-mapping, user
is allowed to arbitrarily map/remap/unmap parts of mapped memory, arbitrarily
splitting it into multiple non-contiguous regions. All this happening without
any control from the users of mmap subsystem. Rather mmap subsystem sends
notifications to original creator of memory mapping through open/close
callbacks, which are optionally specified during initial memory mapping
creation. These callbacks are used to maintain accurate refcount for bpf_map
(see next patch in this series). The problem is that open() callback is not
supposed to fail, because memory-mapped resource is set up and properly
referenced. This is posing a problem for using memory-mapping with BPF maps.

One solution to this is to maintain separate refcount for just memory-mappings
and do single bpf_map_inc/bpf_map_put when it goes from/to zero, respectively.
There are similar use cases in current work on tcp-bpf, necessitating extra
counter as well. This seems like a rather unfortunate and ugly solution that
doesn't scale well to various new use cases.

Another approach to solve this is to use non-failing refcount_t type, which
uses 32-bit counter internally, but, once reaching overflow state at UINT_MAX,
stays there. This utlimately causes memory leak, but prevents use after free.

But given refcounting is not the most performance-critical operation with BPF
maps (it's not used from running BPF program code), we can also just switch to
64-bit counter that can't overflow in practice, potentially disadvantaging
32-bit platforms a tiny bit. This simplifies semantics and allows above
described scenarios to not worry about failing refcount increment operation.

In terms of struct bpf_map size, we are still good and use the same amount of
space:

BEFORE (3 cache lines, 8 bytes of padding at the end):
struct bpf_map {
	const struct bpf_map_ops  * ops __attribute__((__aligned__(64))); /*     0     8 */
	struct bpf_map *           inner_map_meta;       /*     8     8 */
	void *                     security;             /*    16     8 */
	enum bpf_map_type  map_type;                     /*    24     4 */
	u32                        key_size;             /*    28     4 */
	u32                        value_size;           /*    32     4 */
	u32                        max_entries;          /*    36     4 */
	u32                        map_flags;            /*    40     4 */
	int                        spin_lock_off;        /*    44     4 */
	u32                        id;                   /*    48     4 */
	int                        numa_node;            /*    52     4 */
	u32                        btf_key_type_id;      /*    56     4 */
	u32                        btf_value_type_id;    /*    60     4 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	struct btf *               btf;                  /*    64     8 */
	struct bpf_map_memory memory;                    /*    72    16 */
	bool                       unpriv_array;         /*    88     1 */
	bool                       frozen;               /*    89     1 */

	/* XXX 38 bytes hole, try to pack */

	/* --- cacheline 2 boundary (128 bytes) --- */
	atomic_t                   refcnt __attribute__((__aligned__(64))); /*   128     4 */
	atomic_t                   usercnt;              /*   132     4 */
	struct work_struct work;                         /*   136    32 */
	char                       name[16];             /*   168    16 */

	/* size: 192, cachelines: 3, members: 21 */
	/* sum members: 146, holes: 1, sum holes: 38 */
	/* padding: 8 */
	/* forced alignments: 2, forced holes: 1, sum forced holes: 38 */
} __attribute__((__aligned__(64)));

AFTER (same 3 cache lines, no extra padding now):
struct bpf_map {
	const struct bpf_map_ops  * ops __attribute__((__aligned__(64))); /*     0     8 */
	struct bpf_map *           inner_map_meta;       /*     8     8 */
	void *                     security;             /*    16     8 */
	enum bpf_map_type  map_type;                     /*    24     4 */
	u32                        key_size;             /*    28     4 */
	u32                        value_size;           /*    32     4 */
	u32                        max_entries;          /*    36     4 */
	u32                        map_flags;            /*    40     4 */
	int                        spin_lock_off;        /*    44     4 */
	u32                        id;                   /*    48     4 */
	int                        numa_node;            /*    52     4 */
	u32                        btf_key_type_id;      /*    56     4 */
	u32                        btf_value_type_id;    /*    60     4 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	struct btf *               btf;                  /*    64     8 */
	struct bpf_map_memory memory;                    /*    72    16 */
	bool                       unpriv_array;         /*    88     1 */
	bool                       frozen;               /*    89     1 */

	/* XXX 38 bytes hole, try to pack */

	/* --- cacheline 2 boundary (128 bytes) --- */
	atomic64_t                 refcnt __attribute__((__aligned__(64))); /*   128     8 */
	atomic64_t                 usercnt;              /*   136     8 */
	struct work_struct work;                         /*   144    32 */
	char                       name[16];             /*   176    16 */

	/* size: 192, cachelines: 3, members: 21 */
	/* sum members: 154, holes: 1, sum holes: 38 */
	/* forced alignments: 2, forced holes: 1, sum forced holes: 38 */
} __attribute__((__aligned__(64)));

This patch, while modifying all users of bpf_map_inc, also cleans up its
interface to match bpf_map_put with separate operations for bpf_map_inc and
bpf_map_inc_with_uref (to match bpf_map_put and bpf_map_put_with_uref,
respectively). Also, given there are no users of bpf_map_inc_not_zero
specifying uref=true, remove uref flag and default to uref=false internally.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-2-andriin@fb.com
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c |  4 +-
 include/linux/bpf.h                              | 10 ++---
 kernel/bpf/inode.c                               |  2 +-
 kernel/bpf/map_in_map.c                          |  2 +-
 kernel/bpf/syscall.c                             | 51 ++++++++++--------------
 kernel/bpf/verifier.c                            |  6 +--
 kernel/bpf/xskmap.c                              |  6 +--
 net/core/bpf_sk_storage.c                        |  2 +-
 8 files changed, 34 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 88fab6a82acf..06927ba5a3ae 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -46,9 +46,7 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	/* Grab a single ref to the map for our record.  The prog destroy ndo
 	 * happens after free_used_maps().
 	 */
-	map = bpf_map_inc(map, false);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	bpf_map_inc(map);
 
 	record = kmalloc(sizeof(*record), GFP_KERNEL);
 	if (!record) {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b81cde47314..34a34445c009 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -103,8 +103,8 @@ struct bpf_map {
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
 	 */
-	atomic_t refcnt ____cacheline_aligned;
-	atomic_t usercnt;
+	atomic64_t refcnt ____cacheline_aligned;
+	atomic64_t usercnt;
 	struct work_struct work;
 	char name[BPF_OBJ_NAME_LEN];
 };
@@ -783,9 +783,9 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
-struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
-struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map,
-						   bool uref);
+void bpf_map_inc(struct bpf_map *map);
+void bpf_map_inc_with_uref(struct bpf_map *map);
+struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index a70f7209cda3..2f17f24258dc 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 		raw = bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
-		raw = bpf_map_inc(raw, true);
+		bpf_map_inc_with_uref(raw);
 		break;
 	default:
 		WARN_ON_ONCE(1);
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index fab4fb134547..4cbe987be35b 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -98,7 +98,7 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 		return inner_map;
 
 	if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
-		inner_map = bpf_map_inc(inner_map, false);
+		bpf_map_inc(inner_map);
 	else
 		inner_map = ERR_PTR(-EINVAL);
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c88c815c2154..20030751b7a2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -311,7 +311,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 static void bpf_map_put_uref(struct bpf_map *map)
 {
-	if (atomic_dec_and_test(&map->usercnt)) {
+	if (atomic64_dec_and_test(&map->usercnt)) {
 		if (map->ops->map_release_uref)
 			map->ops->map_release_uref(map);
 	}
@@ -322,7 +322,7 @@ static void bpf_map_put_uref(struct bpf_map *map)
  */
 static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
 {
-	if (atomic_dec_and_test(&map->refcnt)) {
+	if (atomic64_dec_and_test(&map->refcnt)) {
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map, do_idr_lock);
 		btf_put(map->btf);
@@ -575,8 +575,8 @@ static int map_create(union bpf_attr *attr)
 	if (err)
 		goto free_map;
 
-	atomic_set(&map->refcnt, 1);
-	atomic_set(&map->usercnt, 1);
+	atomic64_set(&map->refcnt, 1);
+	atomic64_set(&map->usercnt, 1);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
@@ -653,21 +653,19 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-/* prog's and map's refcnt limit */
-#define BPF_MAX_REFCNT 32768
-
-struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
+void bpf_map_inc(struct bpf_map *map)
 {
-	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
-		atomic_dec(&map->refcnt);
-		return ERR_PTR(-EBUSY);
-	}
-	if (uref)
-		atomic_inc(&map->usercnt);
-	return map;
+	atomic64_inc(&map->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_map_inc);
 
+void bpf_map_inc_with_uref(struct bpf_map *map)
+{
+	atomic64_inc(&map->refcnt);
+	atomic64_inc(&map->usercnt);
+}
+EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref);
+
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
@@ -677,38 +675,30 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	map = bpf_map_inc(map, true);
+	bpf_map_inc_with_uref(map);
 	fdput(f);
 
 	return map;
 }
 
 /* map_idr_lock should have been held */
-static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map,
-					      bool uref)
+static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
 {
 	int refold;
 
-	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
-
-	if (refold >= BPF_MAX_REFCNT) {
-		__bpf_map_put(map, false);
-		return ERR_PTR(-EBUSY);
-	}
-
+	refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0);
 	if (!refold)
 		return ERR_PTR(-ENOENT);
-
 	if (uref)
-		atomic_inc(&map->usercnt);
+		atomic64_inc(&map->usercnt);
 
 	return map;
 }
 
-struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
+struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map)
 {
 	spin_lock_bh(&map_idr_lock);
-	map = __bpf_map_inc_not_zero(map, uref);
+	map = __bpf_map_inc_not_zero(map, false);
 	spin_unlock_bh(&map_idr_lock);
 
 	return map;
@@ -1455,6 +1445,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
+/* prog's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
 struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
 {
 	if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e9dc95a18d44..9f59f7a19dd0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8179,11 +8179,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_used_maps()
 			 */
-			map = bpf_map_inc(map, false);
-			if (IS_ERR(map)) {
-				fdput(f);
-				return PTR_ERR(map);
-			}
+			bpf_map_inc(map);
 
 			aux->map_index = env->used_map_cnt;
 			env->used_maps[env->used_map_cnt++] = map;
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index da16c30868f3..90c4fce1c981 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -11,10 +11,8 @@
 
 int xsk_map_inc(struct xsk_map *map)
 {
-	struct bpf_map *m = &map->map;
-
-	m = bpf_map_inc(m, false);
-	return PTR_ERR_OR_ZERO(m);
+	bpf_map_inc(&map->map);
+	return 0;
 }
 
 void xsk_map_put(struct xsk_map *map)
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index da5639a5bd3b..458be6b3eda9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -798,7 +798,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 		 * Try to grab map refcnt to make sure that it's still
 		 * alive and prevent concurrent removal.
 		 */
-		map = bpf_map_inc_not_zero(&smap->map, false);
+		map = bpf_map_inc_not_zero(&smap->map);
 		if (IS_ERR(map))
 			continue;
 
-- 
cgit v1.2.3


From 85192dbf4de08795afe2b88e52a36fc6abfc3dba Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Sun, 17 Nov 2019 09:28:03 -0800
Subject: bpf: Convert bpf_prog refcnt to atomic64_t

Similarly to bpf_map's refcnt/usercnt, convert bpf_prog's refcnt to atomic64
and remove artificial 32k limit. This allows to make bpf_prog's refcounting
non-failing, simplifying logic of users of bpf_prog_add/bpf_prog_inc.

Validated compilation by running allyesconfig kernel build.

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-3-andriin@fb.com
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         |  9 ++-----
 drivers/net/ethernet/cavium/thunder/nicvf_main.c  |  9 ++-----
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c  |  7 ++----
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c    | 24 +++++-------------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 18 ++++----------
 drivers/net/ethernet/qlogic/qede/qede_main.c      |  8 ++----
 drivers/net/virtio_net.c                          |  7 ++----
 include/linux/bpf.h                               | 13 ++++------
 kernel/bpf/inode.c                                |  5 ++--
 kernel/bpf/syscall.c                              | 30 +++++++----------------
 kernel/events/core.c                              |  7 ++----
 11 files changed, 40 insertions(+), 97 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c07172429c70..9da4fbee3cf7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3171,13 +3171,8 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
 	bnxt_init_rxbd_pages(ring, type);
 
 	if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) {
-		rxr->xdp_prog = bpf_prog_add(bp->xdp_prog, 1);
-		if (IS_ERR(rxr->xdp_prog)) {
-			int rc = PTR_ERR(rxr->xdp_prog);
-
-			rxr->xdp_prog = NULL;
-			return rc;
-		}
+		bpf_prog_add(bp->xdp_prog, 1);
+		rxr->xdp_prog = bp->xdp_prog;
 	}
 	prod = rxr->rx_prod;
 	for (i = 0; i < bp->rx_ring_size; i++) {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 40a44dcb3d9b..f28409279ea4 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1876,13 +1876,8 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 
 	if (nic->xdp_prog) {
 		/* Attach BPF program */
-		nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
-		if (!IS_ERR(nic->xdp_prog)) {
-			bpf_attached = true;
-		} else {
-			ret = PTR_ERR(nic->xdp_prog);
-			nic->xdp_prog = NULL;
-		}
+		bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
+		bpf_attached = true;
 	}
 
 	/* Calculate Tx queues needed for XDP and network stack */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index c26c0a7cbb6b..acc56606d3a5 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1807,11 +1807,8 @@ static int setup_xdp(struct net_device *dev, struct bpf_prog *prog)
 	if (prog && !xdp_mtu_valid(priv, dev->mtu))
 		return -EINVAL;
 
-	if (prog) {
-		prog = bpf_prog_add(prog, priv->num_channels);
-		if (IS_ERR(prog))
-			return PTR_ERR(prog);
-	}
+	if (prog)
+		bpf_prog_add(prog, priv->num_channels);
 
 	up = netif_running(dev);
 	need_update = (!!priv->xdp_prog != !!prog);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 40ec5acf79c0..d4697beeacc2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2286,11 +2286,7 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
 		lockdep_is_held(&priv->mdev->state_lock));
 
 	if (xdp_prog && carry_xdp_prog) {
-		xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num);
-		if (IS_ERR(xdp_prog)) {
-			mlx4_en_free_resources(tmp);
-			return PTR_ERR(xdp_prog);
-		}
+		bpf_prog_add(xdp_prog, tmp->rx_ring_num);
 		for (i = 0; i < tmp->rx_ring_num; i++)
 			rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog,
 					   xdp_prog);
@@ -2782,11 +2778,9 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 	 * program for a new one.
 	 */
 	if (priv->tx_ring_num[TX_XDP] == xdp_ring_num) {
-		if (prog) {
-			prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
-			if (IS_ERR(prog))
-				return PTR_ERR(prog);
-		}
+		if (prog)
+			bpf_prog_add(prog, priv->rx_ring_num - 1);
+
 		mutex_lock(&mdev->state_lock);
 		for (i = 0; i < priv->rx_ring_num; i++) {
 			old_prog = rcu_dereference_protected(
@@ -2807,13 +2801,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 	if (!tmp)
 		return -ENOMEM;
 
-	if (prog) {
-		prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
-		if (IS_ERR(prog)) {
-			err = PTR_ERR(prog);
-			goto out;
-		}
-	}
+	if (prog)
+		bpf_prog_add(prog, priv->rx_ring_num - 1);
 
 	mutex_lock(&mdev->state_lock);
 	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
@@ -2862,7 +2851,6 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 
 unlock_out:
 	mutex_unlock(&mdev->state_lock);
-out:
 	kfree(tmp);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 772bfdbdeb9c..1d4a66fb466a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -408,12 +408,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		rq->stats = &c->priv->channel_stats[c->ix].rq;
 	INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work);
 
-	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
-	if (IS_ERR(rq->xdp_prog)) {
-		err = PTR_ERR(rq->xdp_prog);
-		rq->xdp_prog = NULL;
-		goto err_rq_wq_destroy;
-	}
+	if (params->xdp_prog)
+		bpf_prog_inc(params->xdp_prog);
+	rq->xdp_prog = params->xdp_prog;
 
 	rq_xdp_ix = rq->ix;
 	if (xsk)
@@ -4406,16 +4403,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* no need for full reset when exchanging programs */
 	reset = (!priv->channels.params.xdp_prog || !prog);
 
-	if (was_opened && !reset) {
+	if (was_opened && !reset)
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
 		 */
-		prog = bpf_prog_add(prog, priv->channels.num);
-		if (IS_ERR(prog)) {
-			err = PTR_ERR(prog);
-			goto unlock;
-		}
-	}
+		bpf_prog_add(prog, priv->channels.num);
 
 	if (was_opened && reset) {
 		struct mlx5e_channels new_channels = {};
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8d1c208f778f..1e26964fe4e9 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2107,12 +2107,8 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats)
 			if (rc)
 				goto out;
 
-			fp->rxq->xdp_prog = bpf_prog_add(edev->xdp_prog, 1);
-			if (IS_ERR(fp->rxq->xdp_prog)) {
-				rc = PTR_ERR(fp->rxq->xdp_prog);
-				fp->rxq->xdp_prog = NULL;
-				goto out;
-			}
+			bpf_prog_add(edev->xdp_prog, 1);
+			fp->rxq->xdp_prog = edev->xdp_prog;
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5a635f028bdc..4d7d5434cc5d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2445,11 +2445,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	if (!prog && !old_prog)
 		return 0;
 
-	if (prog) {
-		prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
-		if (IS_ERR(prog))
-			return PTR_ERR(prog);
-	}
+	if (prog)
+		bpf_prog_add(prog, vi->max_queue_pairs - 1);
 
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 34a34445c009..fb606dc61a3a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -485,7 +485,7 @@ struct bpf_func_info_aux {
 };
 
 struct bpf_prog_aux {
-	atomic_t refcnt;
+	atomic64_t refcnt;
 	u32 used_map_cnt;
 	u32 max_ctx_offset;
 	u32 max_pkt_offset;
@@ -770,9 +770,9 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops;
 struct bpf_prog *bpf_prog_get(u32 ufd);
 struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
 				       bool attach_drv);
-struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i);
+void bpf_prog_add(struct bpf_prog *prog, int i);
 void bpf_prog_sub(struct bpf_prog *prog, int i);
-struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog);
+void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 int __bpf_prog_charge(struct user_struct *user, u32 pages);
@@ -912,10 +912,8 @@ static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd,
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog,
-							  int i)
+static inline void bpf_prog_add(struct bpf_prog *prog, int i)
 {
-	return ERR_PTR(-EOPNOTSUPP);
 }
 
 static inline void bpf_prog_sub(struct bpf_prog *prog, int i)
@@ -926,9 +924,8 @@ static inline void bpf_prog_put(struct bpf_prog *prog)
 {
 }
 
-static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog)
+static inline void bpf_prog_inc(struct bpf_prog *prog)
 {
-	return ERR_PTR(-EOPNOTSUPP);
 }
 
 static inline struct bpf_prog *__must_check
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 2f17f24258dc..ecf42bec38c0 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,7 +31,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 {
 	switch (type) {
 	case BPF_TYPE_PROG:
-		raw = bpf_prog_inc(raw);
+		bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
 		bpf_map_inc_with_uref(raw);
@@ -534,7 +534,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type
 	if (!bpf_prog_get_ok(prog, &type, false))
 		return ERR_PTR(-EINVAL);
 
-	return bpf_prog_inc(prog);
+	bpf_prog_inc(prog);
+	return prog;
 }
 
 struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 20030751b7a2..52fe4bacb330 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1339,7 +1339,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
-	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+	if (atomic64_dec_and_test(&prog->aux->refcnt)) {
 		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
@@ -1445,16 +1445,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
-/* prog's refcnt limit */
-#define BPF_MAX_REFCNT 32768
-
-struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
+void bpf_prog_add(struct bpf_prog *prog, int i)
 {
-	if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
-		atomic_sub(i, &prog->aux->refcnt);
-		return ERR_PTR(-EBUSY);
-	}
-	return prog;
+	atomic64_add(i, &prog->aux->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_add);
 
@@ -1465,13 +1458,13 @@ void bpf_prog_sub(struct bpf_prog *prog, int i)
 	 * path holds a reference to the program, thus atomic_sub() can
 	 * be safely used in such cases!
 	 */
-	WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
+	WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_sub);
 
-struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+void bpf_prog_inc(struct bpf_prog *prog)
 {
-	return bpf_prog_add(prog, 1);
+	atomic64_inc(&prog->aux->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc);
 
@@ -1480,12 +1473,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
-
-	if (refold >= BPF_MAX_REFCNT) {
-		__bpf_prog_put(prog, false);
-		return ERR_PTR(-EBUSY);
-	}
+	refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (!refold)
 		return ERR_PTR(-ENOENT);
@@ -1523,7 +1511,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
 		goto out;
 	}
 
-	prog = bpf_prog_inc(prog);
+	bpf_prog_inc(prog);
 out:
 	fdput(f);
 	return prog;
@@ -1714,7 +1702,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->orig_prog = NULL;
 	prog->jited = 0;
 
-	atomic_set(&prog->aux->refcnt, 1);
+	atomic64_set(&prog->aux->refcnt, 1);
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
 	if (bpf_prog_is_dev_bound(prog->aux)) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index aec8dba2bea4..73c616876597 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10477,12 +10477,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		context = parent_event->overflow_handler_context;
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING)
 		if (overflow_handler == bpf_overflow_handler) {
-			struct bpf_prog *prog = bpf_prog_inc(parent_event->prog);
+			struct bpf_prog *prog = parent_event->prog;
 
-			if (IS_ERR(prog)) {
-				err = PTR_ERR(prog);
-				goto err_ns;
-			}
+			bpf_prog_inc(prog);
 			event->prog = prog;
 			event->orig_overflow_handler =
 				parent_event->orig_overflow_handler;
-- 
cgit v1.2.3


From fc9702273e2edb90400a34b3be76f7b08fa3344b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Sun, 17 Nov 2019 09:28:04 -0800
Subject: bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY

Add ability to memory-map contents of BPF array map. This is extremely useful
for working with BPF global data from userspace programs. It allows to avoid
typical bpf_map_{lookup,update}_elem operations, improving both performance
and usability.

There had to be special considerations for map freezing, to avoid having
writable memory view into a frozen map. To solve this issue, map freezing and
mmap-ing is happening under mutex now:
  - if map is already frozen, no writable mapping is allowed;
  - if map has writable memory mappings active (accounted in map->writecnt),
    map freezing will keep failing with -EBUSY;
  - once number of writable memory mappings drops to zero, map freezing can be
    performed again.

Only non-per-CPU plain arrays are supported right now. Maps with spinlocks
can't be memory mapped either.

For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc()
to be mmap()'able. We also need to make sure that array data memory is
page-sized and page-aligned, so we over-allocate memory in such a way that
struct bpf_array is at the end of a single page of memory with array->value
being aligned with the start of the second page. On deallocation we need to
accomodate this memory arrangement to free vmalloc()'ed memory correctly.

One important consideration regarding how memory-mapping subsystem functions.
Memory-mapping subsystem provides few optional callbacks, among them open()
and close().  close() is called for each memory region that is unmapped, so
that users can decrease their reference counters and free up resources, if
necessary. open() is *almost* symmetrical: it's called for each memory region
that is being mapped, **except** the very first one. So bpf_map_mmap does
initial refcnt bump, while open() will do any extra ones after that. Thus
number of close() calls is equal to number of open() calls plus one more.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
---
 include/linux/bpf.h            | 11 +++--
 include/linux/vmalloc.h        |  1 +
 include/uapi/linux/bpf.h       |  3 ++
 kernel/bpf/arraymap.c          | 58 ++++++++++++++++++++++---
 kernel/bpf/syscall.c           | 99 ++++++++++++++++++++++++++++++++++++++++--
 mm/vmalloc.c                   | 20 +++++++++
 tools/include/uapi/linux/bpf.h |  3 ++
 7 files changed, 183 insertions(+), 12 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fb606dc61a3a..e913dd5946ae 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -12,6 +12,7 @@
 #include <linux/err.h>
 #include <linux/rbtree_latch.h>
 #include <linux/numa.h>
+#include <linux/mm_types.h>
 #include <linux/wait.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/refcount.h>
@@ -68,6 +69,7 @@ struct bpf_map_ops {
 				     u64 *imm, u32 off);
 	int (*map_direct_value_meta)(const struct bpf_map *map,
 				     u64 imm, u32 *off);
+	int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
 };
 
 struct bpf_map_memory {
@@ -96,9 +98,10 @@ struct bpf_map {
 	u32 btf_value_type_id;
 	struct btf *btf;
 	struct bpf_map_memory memory;
+	char name[BPF_OBJ_NAME_LEN];
 	bool unpriv_array;
-	bool frozen; /* write-once */
-	/* 48 bytes hole */
+	bool frozen; /* write-once; write-protected by freeze_mutex */
+	/* 22 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
@@ -106,7 +109,8 @@ struct bpf_map {
 	atomic64_t refcnt ____cacheline_aligned;
 	atomic64_t usercnt;
 	struct work_struct work;
-	char name[BPF_OBJ_NAME_LEN];
+	struct mutex freeze_mutex;
+	u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -795,6 +799,7 @@ void bpf_map_charge_finish(struct bpf_map_memory *mem);
 void bpf_map_charge_move(struct bpf_map_memory *dst,
 			 struct bpf_map_memory *src);
 void *bpf_map_area_alloc(size_t size, int numa_node);
+void *bpf_map_area_mmapable_alloc(size_t size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 4e7809408073..b4c58a191eb1 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -93,6 +93,7 @@ extern void *vzalloc(unsigned long size);
 extern void *vmalloc_user(unsigned long size);
 extern void *vmalloc_node(unsigned long size, int node);
 extern void *vzalloc_node(unsigned long size, int node);
+extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags);
 extern void *vmalloc_exec(unsigned long size);
 extern void *vmalloc_32(unsigned long size);
 extern void *vmalloc_32_user(unsigned long size);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4842a134b202..dbbcf0b02970 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -348,6 +348,9 @@ enum bpf_attach_type {
 /* Clone map from listener for newly accepted socket */
 #define BPF_F_CLONE		(1U << 9)
 
+/* Enable memory-mapping BPF map */
+#define BPF_F_MMAPABLE		(1U << 10)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1c65ce0098a9..a42097c36b0c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -14,7 +14,7 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
+	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -59,6 +59,10 @@ int array_map_alloc_check(union bpf_attr *attr)
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return -EINVAL;
 
+	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
+	    attr->map_flags & BPF_F_MMAPABLE)
+		return -EINVAL;
+
 	if (attr->value_size > KMALLOC_MAX_SIZE)
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements.
@@ -102,10 +106,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	}
 
 	array_size = sizeof(*array);
-	if (percpu)
+	if (percpu) {
 		array_size += (u64) max_entries * sizeof(void *);
-	else
-		array_size += (u64) max_entries * elem_size;
+	} else {
+		/* rely on vmalloc() to return page-aligned memory and
+		 * ensure array->value is exactly page-aligned
+		 */
+		if (attr->map_flags & BPF_F_MMAPABLE) {
+			array_size = PAGE_ALIGN(array_size);
+			array_size += PAGE_ALIGN((u64) max_entries * elem_size);
+		} else {
+			array_size += (u64) max_entries * elem_size;
+		}
+	}
 
 	/* make sure there is no u32 overflow later in round_up() */
 	cost = array_size;
@@ -117,7 +130,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
-	array = bpf_map_area_alloc(array_size, numa_node);
+	if (attr->map_flags & BPF_F_MMAPABLE) {
+		void *data;
+
+		/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
+		data = bpf_map_area_mmapable_alloc(array_size, numa_node);
+		if (!data) {
+			bpf_map_charge_finish(&mem);
+			return ERR_PTR(-ENOMEM);
+		}
+		array = data + PAGE_ALIGN(sizeof(struct bpf_array))
+			- offsetof(struct bpf_array, value);
+	} else {
+		array = bpf_map_area_alloc(array_size, numa_node);
+	}
 	if (!array) {
 		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
@@ -350,6 +376,11 @@ static int array_map_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
+static void *array_map_vmalloc_addr(struct bpf_array *array)
+{
+	return (void *)round_down((unsigned long)array, PAGE_SIZE);
+}
+
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void array_map_free(struct bpf_map *map)
 {
@@ -365,7 +396,10 @@ static void array_map_free(struct bpf_map *map)
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
-	bpf_map_area_free(array);
+	if (array->map.map_flags & BPF_F_MMAPABLE)
+		bpf_map_area_free(array_map_vmalloc_addr(array));
+	else
+		bpf_map_area_free(array);
 }
 
 static void array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -444,6 +478,17 @@ static int array_map_check_btf(const struct bpf_map *map,
 	return 0;
 }
 
+int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
+
+	if (!(map->map_flags & BPF_F_MMAPABLE))
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+}
+
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -455,6 +500,7 @@ const struct bpf_map_ops array_map_ops = {
 	.map_gen_lookup = array_map_gen_lookup,
 	.map_direct_value_addr = array_map_direct_value_addr,
 	.map_direct_value_meta = array_map_direct_value_meta,
+	.map_mmap = array_map_mmap,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
 };
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 52fe4bacb330..bac3becf9f90 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -127,7 +127,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-void *bpf_map_area_alloc(size_t size, int numa_node)
+static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -142,18 +142,33 @@ void *bpf_map_area_alloc(size_t size, int numa_node)
 	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
 
-	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+	/* kmalloc()'ed memory can't be mmap()'ed */
+	if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
 		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
 				    numa_node);
 		if (area != NULL)
 			return area;
 	}
-
+	if (mmapable) {
+		BUG_ON(!PAGE_ALIGNED(size));
+		return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL |
+					       __GFP_RETRY_MAYFAIL | flags);
+	}
 	return __vmalloc_node_flags_caller(size, numa_node,
 					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
 					   flags, __builtin_return_address(0));
 }
 
+void *bpf_map_area_alloc(size_t size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, false);
+}
+
+void *bpf_map_area_mmapable_alloc(size_t size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, true);
+}
+
 void bpf_map_area_free(void *area)
 {
 	kvfree(area);
@@ -425,6 +440,74 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
 	return -EINVAL;
 }
 
+/* called for any extra memory-mapped regions (except initial) */
+static void bpf_map_mmap_open(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt++;
+		mutex_unlock(&map->freeze_mutex);
+	}
+}
+
+/* called for all unmapped memory region (including initial) */
+static void bpf_map_mmap_close(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt--;
+		mutex_unlock(&map->freeze_mutex);
+	}
+
+	bpf_map_put_with_uref(map);
+}
+
+static const struct vm_operations_struct bpf_map_default_vmops = {
+	.open		= bpf_map_mmap_open,
+	.close		= bpf_map_mmap_close,
+};
+
+static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct bpf_map *map = filp->private_data;
+	int err;
+
+	if (!map->ops->map_mmap || map_value_has_spin_lock(map))
+		return -ENOTSUPP;
+
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	mutex_lock(&map->freeze_mutex);
+
+	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
+		err = -EPERM;
+		goto out;
+	}
+
+	/* set default open/close callbacks */
+	vma->vm_ops = &bpf_map_default_vmops;
+	vma->vm_private_data = map;
+
+	err = map->ops->map_mmap(map, vma);
+	if (err)
+		goto out;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE)
+		map->writecnt++;
+out:
+	mutex_unlock(&map->freeze_mutex);
+	return err;
+}
+
 const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
@@ -432,6 +515,7 @@ const struct file_operations bpf_map_fops = {
 	.release	= bpf_map_release,
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
+	.mmap		= bpf_map_mmap,
 };
 
 int bpf_map_new_fd(struct bpf_map *map, int flags)
@@ -577,6 +661,7 @@ static int map_create(union bpf_attr *attr)
 
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
+	mutex_init(&map->freeze_mutex);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
@@ -1163,6 +1248,13 @@ static int map_freeze(const union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+
+	mutex_lock(&map->freeze_mutex);
+
+	if (map->writecnt) {
+		err = -EBUSY;
+		goto err_put;
+	}
 	if (READ_ONCE(map->frozen)) {
 		err = -EBUSY;
 		goto err_put;
@@ -1174,6 +1266,7 @@ static int map_freeze(const union bpf_attr *attr)
 
 	WRITE_ONCE(map->frozen, true);
 err_put:
+	mutex_unlock(&map->freeze_mutex);
 	fdput(f);
 	return err;
 }
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a3c70e275f4e..4a7d7459c4f9 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2671,6 +2671,26 @@ void *vzalloc_node(unsigned long size, int node)
 }
 EXPORT_SYMBOL(vzalloc_node);
 
+/**
+ * vmalloc_user_node_flags - allocate memory for userspace on a specific node
+ * @size: allocation size
+ * @node: numa node
+ * @flags: flags for the page level allocator
+ *
+ * The resulting memory area is zeroed so it can be mapped to userspace
+ * without leaking data.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags)
+{
+	return __vmalloc_node_range(size, SHMLBA,  VMALLOC_START, VMALLOC_END,
+				    flags | __GFP_ZERO, PAGE_KERNEL,
+				    VM_USERMAP, node,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(vmalloc_user_node_flags);
+
 /**
  * vmalloc_exec - allocate virtually contiguous, executable memory
  * @size:	  allocation size
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4842a134b202..dbbcf0b02970 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -348,6 +348,9 @@ enum bpf_attach_type {
 /* Clone map from listener for newly accepted socket */
 #define BPF_F_CLONE		(1U << 9)
 
+/* Enable memory-mapping BPF map */
+#define BPF_F_MMAPABLE		(1U << 10)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
-- 
cgit v1.2.3


From 7fe74b436236b17ac57e46527166d22bcc230175 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Sun, 17 Nov 2019 09:28:05 -0800
Subject: libbpf: Make global data internal arrays mmap()-able, if possible

Add detection of BPF_F_MMAPABLE flag support for arrays and add it as an extra
flag to internal global data maps, if supported by kernel. This allows users
to memory-map global data and use it without BPF map operations, greatly
simplifying user experience.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-5-andriin@fb.com
---
 tools/lib/bpf/libbpf.c | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7132c6bdec02..15e91a1d6c11 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -142,6 +142,8 @@ struct bpf_capabilities {
 	__u32 btf_func:1;
 	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
 	__u32 btf_datasec:1;
+	/* BPF_F_MMAPABLE is supported for arrays */
+	__u32 array_mmap:1;
 };
 
 /*
@@ -857,8 +859,6 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		pr_warn("failed to alloc map name\n");
 		return -ENOMEM;
 	}
-	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
-		 map_name, map->sec_idx, map->sec_offset);
 
 	def = &map->def;
 	def->type = BPF_MAP_TYPE_ARRAY;
@@ -866,6 +866,12 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	def->value_size = data->d_size;
 	def->max_entries = 1;
 	def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
+	if (obj->caps.array_mmap)
+		def->map_flags |= BPF_F_MMAPABLE;
+
+	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
+		 map_name, map->sec_idx, map->sec_offset, def->map_flags);
+
 	if (data_buff) {
 		*data_buff = malloc(data->d_size);
 		if (!*data_buff) {
@@ -2161,6 +2167,27 @@ static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
 	return 0;
 }
 
+static int bpf_object__probe_array_mmap(struct bpf_object *obj)
+{
+	struct bpf_create_map_attr attr = {
+		.map_type = BPF_MAP_TYPE_ARRAY,
+		.map_flags = BPF_F_MMAPABLE,
+		.key_size = sizeof(int),
+		.value_size = sizeof(int),
+		.max_entries = 1,
+	};
+	int fd;
+
+	fd = bpf_create_map_xattr(&attr);
+	if (fd >= 0) {
+		obj->caps.array_mmap = 1;
+		close(fd);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int
 bpf_object__probe_caps(struct bpf_object *obj)
 {
@@ -2169,6 +2196,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
 		bpf_object__probe_global_data,
 		bpf_object__probe_btf_func,
 		bpf_object__probe_btf_datasec,
+		bpf_object__probe_array_mmap,
 	};
 	int i, ret;
 
-- 
cgit v1.2.3


From 5051b384523be92925d13694fabbc6bedf2f907b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Sun, 17 Nov 2019 09:28:06 -0800
Subject: selftests/bpf: Add BPF_TYPE_MAP_ARRAY mmap() tests

Add selftests validating mmap()-ing BPF array maps: both single-element and
multi-element ones. Check that plain bpf_map_update_elem() and
bpf_map_lookup_elem() work correctly with memory-mapped array. Also convert
CO-RE relocation tests to use memory-mapped views of global data.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-6-andriin@fb.com
---
 .../testing/selftests/bpf/prog_tests/core_reloc.c  |  45 +++--
 tools/testing/selftests/bpf/prog_tests/mmap.c      | 220 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_mmap.c      |  45 +++++
 3 files changed, 292 insertions(+), 18 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/mmap.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_mmap.c

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index f94bd071536b..ec9e2fdd6b89 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "progs/core_reloc_types.h"
+#include <sys/mman.h>
 
 #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)
 
@@ -453,8 +454,15 @@ struct data {
 	char out[256];
 };
 
+static size_t roundup_page(size_t sz)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+	return (sz + page_size - 1) / page_size * page_size;
+}
+
 void test_core_reloc(void)
 {
+	const size_t mmap_sz = roundup_page(sizeof(struct data));
 	struct bpf_object_load_attr load_attr = {};
 	struct core_reloc_test_case *test_case;
 	const char *tp_name, *probe_name;
@@ -463,8 +471,8 @@ void test_core_reloc(void)
 	struct bpf_map *data_map;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	const int zero = 0;
-	struct data data;
+	struct data *data;
+	void *mmap_data = NULL;
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
 		test_case = &test_cases[i];
@@ -476,8 +484,7 @@ void test_core_reloc(void)
 		);
 
 		obj = bpf_object__open_file(test_case->bpf_obj_file, &opts);
-		if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
-			  "failed to open '%s': %ld\n",
+		if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n",
 			  test_case->bpf_obj_file, PTR_ERR(obj)))
 			continue;
 
@@ -519,24 +526,22 @@ void test_core_reloc(void)
 		if (CHECK(!data_map, "find_data_map", "data map not found\n"))
 			goto cleanup;
 
-		memset(&data, 0, sizeof(data));
-		memcpy(data.in, test_case->input, test_case->input_len);
-
-		err = bpf_map_update_elem(bpf_map__fd(data_map),
-					  &zero, &data, 0);
-		if (CHECK(err, "update_data_map",
-			  "failed to update .data map: %d\n", err))
+		mmap_data = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+				 MAP_SHARED, bpf_map__fd(data_map), 0);
+		if (CHECK(mmap_data == MAP_FAILED, "mmap",
+			  ".bss mmap failed: %d", errno)) {
+			mmap_data = NULL;
 			goto cleanup;
+		}
+		data = mmap_data;
+
+		memset(mmap_data, 0, sizeof(*data));
+		memcpy(data->in, test_case->input, test_case->input_len);
 
 		/* trigger test run */
 		usleep(1);
 
-		err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &data);
-		if (CHECK(err, "get_result",
-			  "failed to get output data: %d\n", err))
-			goto cleanup;
-
-		equal = memcmp(data.out, test_case->output,
+		equal = memcmp(data->out, test_case->output,
 			       test_case->output_len) == 0;
 		if (CHECK(!equal, "check_result",
 			  "input/output data don't match\n")) {
@@ -548,12 +553,16 @@ void test_core_reloc(void)
 			}
 			for (j = 0; j < test_case->output_len; j++) {
 				printf("output byte #%d: EXP 0x%02hhx GOT 0x%02hhx\n",
-				       j, test_case->output[j], data.out[j]);
+				       j, test_case->output[j], data->out[j]);
 			}
 			goto cleanup;
 		}
 
 cleanup:
+		if (mmap_data) {
+			CHECK_FAIL(munmap(mmap_data, mmap_sz));
+			mmap_data = NULL;
+		}
 		if (!IS_ERR_OR_NULL(link)) {
 			bpf_link__destroy(link);
 			link = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
new file mode 100644
index 000000000000..051a6d48762c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -0,0 +1,220 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <sys/mman.h>
+
+struct map_data {
+	__u64 val[512 * 4];
+};
+
+struct bss_data {
+	__u64 in_val;
+	__u64 out_val;
+};
+
+static size_t roundup_page(size_t sz)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+	return (sz + page_size - 1) / page_size * page_size;
+}
+
+void test_mmap(void)
+{
+	const char *file = "test_mmap.o";
+	const char *probe_name = "raw_tracepoint/sys_enter";
+	const char *tp_name = "sys_enter";
+	const size_t bss_sz = roundup_page(sizeof(struct bss_data));
+	const size_t map_sz = roundup_page(sizeof(struct map_data));
+	const int zero = 0, one = 1, two = 2, far = 1500;
+	const long page_size = sysconf(_SC_PAGE_SIZE);
+	int err, duration = 0, i, data_map_fd;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_link *link = NULL;
+	struct bpf_map *data_map, *bss_map;
+	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
+	volatile struct bss_data *bss_data;
+	volatile struct map_data *map_data;
+	__u64 val = 0;
+
+	obj = bpf_object__open_file("test_mmap.o", NULL);
+	if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n",
+		  file, PTR_ERR(obj)))
+		return;
+	prog = bpf_object__find_program_by_title(obj, probe_name);
+	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name))
+		goto cleanup;
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "failed to load prog '%s': %d\n",
+		  probe_name, err))
+		goto cleanup;
+
+	bss_map = bpf_object__find_map_by_name(obj, "test_mma.bss");
+	if (CHECK(!bss_map, "find_bss_map", ".bss map not found\n"))
+		goto cleanup;
+	data_map = bpf_object__find_map_by_name(obj, "data_map");
+	if (CHECK(!data_map, "find_data_map", "data_map map not found\n"))
+		goto cleanup;
+	data_map_fd = bpf_map__fd(data_map);
+
+	bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+			  bpf_map__fd(bss_map), 0);
+	if (CHECK(bss_mmaped == MAP_FAILED, "bss_mmap",
+		  ".bss mmap failed: %d\n", errno)) {
+		bss_mmaped = NULL;
+		goto cleanup;
+	}
+	/* map as R/W first */
+	map_mmaped = mmap(NULL, map_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+			  data_map_fd, 0);
+	if (CHECK(map_mmaped == MAP_FAILED, "data_mmap",
+		  "data_map mmap failed: %d\n", errno)) {
+		map_mmaped = NULL;
+		goto cleanup;
+	}
+
+	bss_data = bss_mmaped;
+	map_data = map_mmaped;
+
+	CHECK_FAIL(bss_data->in_val);
+	CHECK_FAIL(bss_data->out_val);
+	CHECK_FAIL(map_data->val[0]);
+	CHECK_FAIL(map_data->val[1]);
+	CHECK_FAIL(map_data->val[2]);
+	CHECK_FAIL(map_data->val[far]);
+
+	link = bpf_program__attach_raw_tracepoint(prog, tp_name);
+	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
+		goto cleanup;
+
+	bss_data->in_val = 123;
+	val = 111;
+	CHECK_FAIL(bpf_map_update_elem(data_map_fd, &zero, &val, 0));
+
+	usleep(1);
+
+	CHECK_FAIL(bss_data->in_val != 123);
+	CHECK_FAIL(bss_data->out_val != 123);
+	CHECK_FAIL(map_data->val[0] != 111);
+	CHECK_FAIL(map_data->val[1] != 222);
+	CHECK_FAIL(map_data->val[2] != 123);
+	CHECK_FAIL(map_data->val[far] != 3 * 123);
+
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &zero, &val));
+	CHECK_FAIL(val != 111);
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &one, &val));
+	CHECK_FAIL(val != 222);
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &two, &val));
+	CHECK_FAIL(val != 123);
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &far, &val));
+	CHECK_FAIL(val != 3 * 123);
+
+	/* data_map freeze should fail due to R/W mmap() */
+	err = bpf_map_freeze(data_map_fd);
+	if (CHECK(!err || errno != EBUSY, "no_freeze",
+		  "data_map freeze succeeded: err=%d, errno=%d\n", err, errno))
+		goto cleanup;
+
+	/* unmap R/W mapping */
+	err = munmap(map_mmaped, map_sz);
+	map_mmaped = NULL;
+	if (CHECK(err, "data_map_munmap", "data_map munmap failed: %d\n", errno))
+		goto cleanup;
+
+	/* re-map as R/O now */
+	map_mmaped = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0);
+	if (CHECK(map_mmaped == MAP_FAILED, "data_mmap",
+		  "data_map R/O mmap failed: %d\n", errno)) {
+		map_mmaped = NULL;
+		goto cleanup;
+	}
+	map_data = map_mmaped;
+
+	/* map/unmap in a loop to test ref counting */
+	for (i = 0; i < 10; i++) {
+		int flags = i % 2 ? PROT_READ : PROT_WRITE;
+		void *p;
+
+		p = mmap(NULL, map_sz, flags, MAP_SHARED, data_map_fd, 0);
+		if (CHECK_FAIL(p == MAP_FAILED))
+			goto cleanup;
+		err = munmap(p, map_sz);
+		if (CHECK_FAIL(err))
+			goto cleanup;
+	}
+
+	/* data_map freeze should now succeed due to no R/W mapping */
+	err = bpf_map_freeze(data_map_fd);
+	if (CHECK(err, "freeze", "data_map freeze failed: err=%d, errno=%d\n",
+		  err, errno))
+		goto cleanup;
+
+	/* mapping as R/W now should fail */
+	tmp1 = mmap(NULL, map_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+		    data_map_fd, 0);
+	if (CHECK(tmp1 != MAP_FAILED, "data_mmap", "mmap succeeded\n")) {
+		munmap(tmp1, map_sz);
+		goto cleanup;
+	}
+
+	bss_data->in_val = 321;
+	usleep(1);
+	CHECK_FAIL(bss_data->in_val != 321);
+	CHECK_FAIL(bss_data->out_val != 321);
+	CHECK_FAIL(map_data->val[0] != 111);
+	CHECK_FAIL(map_data->val[1] != 222);
+	CHECK_FAIL(map_data->val[2] != 321);
+	CHECK_FAIL(map_data->val[far] != 3 * 321);
+
+	/* check some more advanced mmap() manipulations */
+
+	/* map all but last page: pages 1-3 mapped */
+	tmp1 = mmap(NULL, 3 * page_size, PROT_READ, MAP_SHARED,
+			  data_map_fd, 0);
+	if (CHECK(tmp1 == MAP_FAILED, "adv_mmap1", "errno %d\n", errno))
+		goto cleanup;
+
+	/* unmap second page: pages 1, 3 mapped */
+	err = munmap(tmp1 + page_size, page_size);
+	if (CHECK(err, "adv_mmap2", "errno %d\n", errno)) {
+		munmap(tmp1, map_sz);
+		goto cleanup;
+	}
+
+	/* map page 2 back */
+	tmp2 = mmap(tmp1 + page_size, page_size, PROT_READ,
+		    MAP_SHARED | MAP_FIXED, data_map_fd, 0);
+	if (CHECK(tmp2 == MAP_FAILED, "adv_mmap3", "errno %d\n", errno)) {
+		munmap(tmp1, page_size);
+		munmap(tmp1 + 2*page_size, page_size);
+		goto cleanup;
+	}
+	CHECK(tmp1 + page_size != tmp2, "adv_mmap4",
+	      "tmp1: %p, tmp2: %p\n", tmp1, tmp2);
+
+	/* re-map all 4 pages */
+	tmp2 = mmap(tmp1, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
+		    data_map_fd, 0);
+	if (CHECK(tmp2 == MAP_FAILED, "adv_mmap5", "errno %d\n", errno)) {
+		munmap(tmp1, 3 * page_size); /* unmap page 1 */
+		goto cleanup;
+	}
+	CHECK(tmp1 != tmp2, "adv_mmap6", "tmp1: %p, tmp2: %p\n", tmp1, tmp2);
+
+	map_data = tmp2;
+	CHECK_FAIL(bss_data->in_val != 321);
+	CHECK_FAIL(bss_data->out_val != 321);
+	CHECK_FAIL(map_data->val[0] != 111);
+	CHECK_FAIL(map_data->val[1] != 222);
+	CHECK_FAIL(map_data->val[2] != 321);
+	CHECK_FAIL(map_data->val[far] != 3 * 321);
+
+	munmap(tmp2, 4 * page_size);
+cleanup:
+	if (bss_mmaped)
+		CHECK_FAIL(munmap(bss_mmaped, bss_sz));
+	if (map_mmaped)
+		CHECK_FAIL(munmap(map_mmaped, map_sz));
+	if (!IS_ERR_OR_NULL(link))
+		bpf_link__destroy(link);
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
new file mode 100644
index 000000000000..0d2ec9fbcf61
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 512 * 4); /* at least 4 pages of data */
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, __u32);
+	__type(value, __u64);
+} data_map SEC(".maps");
+
+static volatile __u64 in_val;
+static volatile __u64 out_val;
+
+SEC("raw_tracepoint/sys_enter")
+int test_mmap(void *ctx)
+{
+	int zero = 0, one = 1, two = 2, far = 1500;
+	__u64 val, *p;
+
+	out_val = in_val;
+
+	/* data_map[2] = in_val; */
+	bpf_map_update_elem(&data_map, &two, (const void *)&in_val, 0);
+
+	/* data_map[1] = data_map[0] * 2; */
+	p = bpf_map_lookup_elem(&data_map, &zero);
+	if (p) {
+		val = (*p) * 2;
+		bpf_map_update_elem(&data_map, &one, &val, 0);
+	}
+
+	/* data_map[far] = in_val * 3; */
+	val = in_val * 3;
+	bpf_map_update_elem(&data_map, &far, &val, 0);
+
+	return 0;
+}
+
-- 
cgit v1.2.3


From 56bf877a508099f16fb78c71a348f39d0dc5fd72 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Mon, 18 Nov 2019 21:25:26 +0100
Subject: selftests, bpf: xdping is not meant to be run standalone
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The actual test to run is test_xdping.sh, which is already in TEST_PROGS.
The xdping program alone is not runnable with 'make run_tests', it
immediatelly fails due to missing arguments.

Move xdping to TEST_GEN_PROGS_EXTENDED in order to be built but not run.

Fixes: cd5385029f1d ("selftests/bpf: measure RTT from xdp using xdping")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/4365c81198f62521344c2215909634407184387e.1573821726.git.jbenc@redhat.com
---
 tools/testing/selftests/bpf/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index b03dc2298fea..d4400fbe6634 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -30,7 +30,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage test_select_reuseport \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
-	test_cgroup_attach xdping test_progs-no_alu32
+	test_cgroup_attach test_progs-no_alu32
 
 # Also test bpf-gcc, if present
 ifneq ($(BPF_GCC),)
@@ -71,7 +71,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
-	test_lirc_mode2_user
+	test_lirc_mode2_user xdping
 
 TEST_CUSTOM_PROGS = urandom_read
 
-- 
cgit v1.2.3


From 3b054b7133b4ad93671c82e8d6185258e3f1a7a5 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Fri, 15 Nov 2019 13:43:23 +0100
Subject: selftests, bpf: Fix test_tc_tunnel hanging

When run_kselftests.sh is run, it hangs after test_tc_tunnel.sh. The reason
is test_tc_tunnel.sh ensures the server ('nc -l') is run all the time,
starting it again every time it is expected to terminate. The exception is
the final client_connect: the server is not started anymore, which ensures
no process is kept running after the test is finished.

For a sit test, though, the script is terminated prematurely without the
final client_connect and the 'nc' process keeps running. This in turn causes
the run_one function in kselftest/runner.sh to hang forever, waiting for the
runaway process to finish.

Ensure a remaining server is terminated on cleanup.

Fixes: f6ad6accaa99 ("selftests/bpf: expand test_tc_tunnel with SIT encap")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/bpf/60919291657a9ee89c708d8aababc28ebe1420be.1573821780.git.jbenc@redhat.com
---
 tools/testing/selftests/bpf/test_tc_tunnel.sh | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index ff0d31d38061..7c76b841b17b 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -62,6 +62,10 @@ cleanup() {
 	if [[ -f "${infile}" ]]; then
 		rm "${infile}"
 	fi
+
+	if [[ -n $server_pid ]]; then
+		kill $server_pid 2> /dev/null
+	fi
 }
 
 server_listen() {
@@ -77,6 +81,7 @@ client_connect() {
 
 verify_data() {
 	wait "${server_pid}"
+	server_pid=
 	# sha1sum returns two fields [sha1] [filepath]
 	# convert to bash array and access first elem
 	insum=($(sha1sum ${infile}))
-- 
cgit v1.2.3


From 2ea2612b987ad703235c92be21d4e98ee9c2c67c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sun, 17 Nov 2019 13:40:36 -0800
Subject: selftests, bpf: Workaround an alu32 sub-register spilling issue

Currently, with latest llvm trunk, selftest test_progs failed obj
file test_seg6_loop.o with the following error in verifier:

  infinite loop detected at insn 76

The byte code sequence looks like below, and noted that alu32 has been
turned off by default for better generated codes in general:

      48:       w3 = 100
      49:       *(u32 *)(r10 - 68) = r3
      ...
  ;             if (tlv.type == SR6_TLV_PADDING) {
      76:       if w3 == 5 goto -18 <LBB0_19>
      ...
      85:       r1 = *(u32 *)(r10 - 68)
  ;     for (int i = 0; i < 100; i++) {
      86:       w1 += -1
      87:       if w1 == 0 goto +5 <LBB0_20>
      88:       *(u32 *)(r10 - 68) = r1

The main reason for verification failure is due to partial spills at
r10 - 68 for induction variable "i".

Current verifier only handles spills with 8-byte values. The above 4-byte
value spill to stack is treated to STACK_MISC and its content is not
saved. For the above example:

    w3 = 100
      R3_w=inv100 fp-64_w=inv1086626730498
    *(u32 *)(r10 - 68) = r3
      R3_w=inv100 fp-64_w=inv1086626730498
    ...
    r1 = *(u32 *)(r10 - 68)
      R1_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff))
      fp-64=inv1086626730498

To resolve this issue, verifier needs to be extended to track sub-registers
in spilling, or llvm needs to enhanced to prevent sub-register spilling
in register allocation phase. The former will increase verifier complexity
and the latter will need some llvm "hacking".

Let us workaround this issue by declaring the induction variable as "long"
type so spilling will happen at non sub-register level. We can revisit this
later if sub-register spilling causes similar or other verification issues.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191117214036.1309510-1-yhs@fb.com
---
 tools/testing/selftests/bpf/progs/test_seg6_loop.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
index c4d104428643..69880c1e7700 100644
--- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
@@ -132,8 +132,10 @@ static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb,
 	*pad_off = 0;
 
 	// we can only go as far as ~10 TLVs due to the BPF max stack size
+	// workaround: define induction variable "i" as "long" instead
+	// of "int" to prevent alu32 sub-register spilling.
 	#pragma clang loop unroll(disable)
-	for (int i = 0; i < 100; i++) {
+	for (long i = 0; i < 100; i++) {
 		struct sr6_tlv_t tlv;
 
 		if (cur_off == *tlv_off)
-- 
cgit v1.2.3


From a25ecd9d1e60241df905b29fb84765eb74545c4f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 18 Nov 2019 11:40:59 +0000
Subject: bpf: Fix memory leak on object 'data'

The error return path on when bpf_fentry_test* tests fail does not
kfree 'data'. Fix this by adding the missing kfree.

Addresses-Coverity: ("Resource leak")

Fixes: faeb2dce084a ("bpf: Add kernel test functions for fentry testing")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118114059.37287-1-colin.king@canonical.com
---
 net/bpf/test_run.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 62933279fbba..915c2d6f7fb9 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -161,8 +161,10 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 	    bpf_fentry_test3(4, 5, 6) != 15 ||
 	    bpf_fentry_test4((void *)7, 8, 9, 10) != 34 ||
 	    bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 ||
-	    bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111)
+	    bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) {
+		kfree(data);
 		return ERR_PTR(-EFAULT);
+	}
 	return data;
 }
 
-- 
cgit v1.2.3


From 4e9b4a6883dd97aff53ae3b08eb900716a5469dc Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 18 Nov 2019 19:03:35 +0100
Subject: s390/bpf: Use relative long branches

Currently maximum JITed code size is limited to 64k, because JIT can
emit only relative short branches, whose range is limited by 64k in both
directions.

Teach JIT to use relative long branches. There are no compare+branch
relative long instructions, so using relative long branches consumes
more space due to having to having to emit an explicit comparison
instruction. Therefore do this only when relative short branch is not
enough.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118180340.68373-2-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 158 ++++++++++++++++++++++++++++++++++---------
 1 file changed, 126 insertions(+), 32 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 7bddb27c81e3..5ee1ebc6e448 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -189,6 +189,12 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	_EMIT4((op) | __pcrel);					\
 })
 
+#define EMIT4_PCREL_RIC(op, mask, target)			\
+({								\
+	int __rel = ((target) - jit->prg) / 2;			\
+	_EMIT4((op) | (mask) << 20 | (__rel & 0xffff));		\
+})
+
 #define _EMIT6(op1, op2)					\
 ({								\
 	if (jit->prg_buf) {					\
@@ -250,17 +256,22 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 
 #define EMIT6_PCREL_RILB(op, b, target)				\
 ({								\
-	int rel = ((target) - jit->prg) / 2;			\
+	unsigned int rel = (int)((target) - jit->prg) / 2;	\
 	_EMIT6((op) | reg_high(b) << 16 | rel >> 16, rel & 0xffff);\
 	REG_SET_SEEN(b);					\
 })
 
 #define EMIT6_PCREL_RIL(op, target)				\
 ({								\
-	int rel = ((target) - jit->prg) / 2;			\
+	unsigned int rel = (int)((target) - jit->prg) / 2;	\
 	_EMIT6((op) | rel >> 16, rel & 0xffff);			\
 })
 
+#define EMIT6_PCREL_RILC(op, mask, target)			\
+({								\
+	EMIT6_PCREL_RIL((op) | (mask) << 20, (target));		\
+})
+
 #define _EMIT6_IMM(op, imm)					\
 ({								\
 	unsigned int __imm = (imm);				\
@@ -322,6 +333,22 @@ static bool is_codegen_pass(struct bpf_jit *jit)
 	return jit->prg_buf;
 }
 
+/*
+ * Return whether "rel" can be encoded as a short PC-relative offset
+ */
+static bool is_valid_rel(int rel)
+{
+	return rel >= -65536 && rel <= 65534;
+}
+
+/*
+ * Return whether "off" can be reached using a short PC-relative offset
+ */
+static bool can_use_rel(struct bpf_jit *jit, int off)
+{
+	return is_valid_rel(off - jit->prg);
+}
+
 /*
  * Fill whole space with illegal instructions
  */
@@ -525,9 +552,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 				 int i, bool extra_pass)
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
-	int jmp_off, last, insn_count = 1;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
+	int last, insn_count = 1;
 	u32 *addrs = jit->addrs;
 	s32 imm = insn->imm;
 	s16 off = insn->off;
@@ -1071,9 +1098,17 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		/* llgf %w1,map.max_entries(%b2) */
 		EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
 			      offsetof(struct bpf_array, map.max_entries));
-		/* clrj %b3,%w1,0xa,label0: if (u32)%b3 >= (u32)%w1 goto out */
-		EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
-				  REG_W1, 0, 0xa);
+		/* if ((u32)%b3 >= (u32)%w1) goto out; */
+		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
+			/* clrj %b3,%w1,0xa,label0 */
+			EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
+					  REG_W1, 0, 0xa);
+		} else {
+			/* clr %b3,%w1 */
+			EMIT2(0x1500, BPF_REG_3, REG_W1);
+			/* brcl 0xa,label0 */
+			EMIT6_PCREL_RILC(0xc0040000, 0xa, jit->labels[0]);
+		}
 
 		/*
 		 * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT)
@@ -1088,9 +1123,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7080000, REG_W0, 1);
 		/* laal %w1,%w0,off(%r15) */
 		EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off);
-		/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
-		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
-				      MAX_TAIL_CALL_CNT, 0, 0x2);
+		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
+			/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
+			EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
+					      MAX_TAIL_CALL_CNT, 0, 0x2);
+		} else {
+			/* clfi %w1,MAX_TAIL_CALL_CNT */
+			EMIT6_IMM(0xc20f0000, REG_W1, MAX_TAIL_CALL_CNT);
+			/* brcl 0x2,label0 */
+			EMIT6_PCREL_RILC(0xc0040000, 0x2, jit->labels[0]);
+		}
 
 		/*
 		 * prog = array->ptrs[index];
@@ -1102,11 +1144,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4(0xb9160000, REG_1, BPF_REG_3);
 		/* sllg %r1,%r1,3: %r1 *= 8 */
 		EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, REG_1, REG_0, 3);
-		/* lg %r1,prog(%b2,%r1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
+		/* ltg %r1,prog(%b2,%r1) */
+		EMIT6_DISP_LH(0xe3000000, 0x0002, REG_1, BPF_REG_2,
 			      REG_1, offsetof(struct bpf_array, ptrs));
-		/* clgij %r1,0,0x8,label0 */
-		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8);
+		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
+			/* brc 0x8,label0 */
+			EMIT4_PCREL_RIC(0xa7040000, 0x8, jit->labels[0]);
+		} else {
+			/* brcl 0x8,label0 */
+			EMIT6_PCREL_RILC(0xc0040000, 0x8, jit->labels[0]);
+		}
 
 		/*
 		 * Restore registers before calling function
@@ -1263,36 +1310,83 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		goto branch_oc;
 branch_ks:
 		is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-		/* lgfi %w1,imm (load sign extend imm) */
-		EMIT6_IMM(0xc0010000, REG_W1, imm);
-		/* crj or cgrj %dst,%w1,mask,off */
-		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
-			    dst_reg, REG_W1, i, off, mask);
+		/* cfi or cgfi %dst,imm */
+		EMIT6_IMM(is_jmp32 ? 0xc20d0000 : 0xc20c0000,
+			  dst_reg, imm);
+		if (!is_first_pass(jit) &&
+		    can_use_rel(jit, addrs[i + off + 1])) {
+			/* brc mask,off */
+			EMIT4_PCREL_RIC(0xa7040000,
+					mask >> 12, addrs[i + off + 1]);
+		} else {
+			/* brcl mask,off */
+			EMIT6_PCREL_RILC(0xc0040000,
+					 mask >> 12, addrs[i + off + 1]);
+		}
 		break;
 branch_ku:
 		is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-		/* lgfi %w1,imm (load sign extend imm) */
-		EMIT6_IMM(0xc0010000, REG_W1, imm);
-		/* clrj or clgrj %dst,%w1,mask,off */
-		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
-			    dst_reg, REG_W1, i, off, mask);
+		/* clfi or clgfi %dst,imm */
+		EMIT6_IMM(is_jmp32 ? 0xc20f0000 : 0xc20e0000,
+			  dst_reg, imm);
+		if (!is_first_pass(jit) &&
+		    can_use_rel(jit, addrs[i + off + 1])) {
+			/* brc mask,off */
+			EMIT4_PCREL_RIC(0xa7040000,
+					mask >> 12, addrs[i + off + 1]);
+		} else {
+			/* brcl mask,off */
+			EMIT6_PCREL_RILC(0xc0040000,
+					 mask >> 12, addrs[i + off + 1]);
+		}
 		break;
 branch_xs:
 		is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-		/* crj or cgrj %dst,%src,mask,off */
-		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
-			    dst_reg, src_reg, i, off, mask);
+		if (!is_first_pass(jit) &&
+		    can_use_rel(jit, addrs[i + off + 1])) {
+			/* crj or cgrj %dst,%src,mask,off */
+			EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
+				    dst_reg, src_reg, i, off, mask);
+		} else {
+			/* cr or cgr %dst,%src */
+			if (is_jmp32)
+				EMIT2(0x1900, dst_reg, src_reg);
+			else
+				EMIT4(0xb9200000, dst_reg, src_reg);
+			/* brcl mask,off */
+			EMIT6_PCREL_RILC(0xc0040000,
+					 mask >> 12, addrs[i + off + 1]);
+		}
 		break;
 branch_xu:
 		is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-		/* clrj or clgrj %dst,%src,mask,off */
-		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
-			    dst_reg, src_reg, i, off, mask);
+		if (!is_first_pass(jit) &&
+		    can_use_rel(jit, addrs[i + off + 1])) {
+			/* clrj or clgrj %dst,%src,mask,off */
+			EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
+				    dst_reg, src_reg, i, off, mask);
+		} else {
+			/* clr or clgr %dst,%src */
+			if (is_jmp32)
+				EMIT2(0x1500, dst_reg, src_reg);
+			else
+				EMIT4(0xb9210000, dst_reg, src_reg);
+			/* brcl mask,off */
+			EMIT6_PCREL_RILC(0xc0040000,
+					 mask >> 12, addrs[i + off + 1]);
+		}
 		break;
 branch_oc:
-		/* brc mask,jmp_off (branch instruction needs 4 bytes) */
-		jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
-		EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
+		if (!is_first_pass(jit) &&
+		    can_use_rel(jit, addrs[i + off + 1])) {
+			/* brc mask,off */
+			EMIT4_PCREL_RIC(0xa7040000,
+					mask >> 12, addrs[i + off + 1]);
+		} else {
+			/* brcl mask,off */
+			EMIT6_PCREL_RILC(0xc0040000,
+					 mask >> 12, addrs[i + off + 1]);
+		}
 		break;
 	}
 	default: /* too complex, give up */
-- 
cgit v1.2.3


From e0491f64795bfc71ef6b13ba6b6fa6e176fa3c23 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 18 Nov 2019 19:03:36 +0100
Subject: s390/bpf: Align literal pool entries

When literal pool size exceeds 512k, it's no longer possible to
reference all the entries in it using a single base register and long
displacement. Therefore, PC-relative lgfrl and lgrl instructions need to
be used.

Unfortunately, they require their arguments to be aligned to 4- and
8-byte boundaries respectively. This generates certain overhead due to
necessary padding bytes. Grouping 4- and 8-byte entries together reduces
the maximum overhead to 6 bytes (2 for aligning 4-byte entries and 4 for
aligning 8-byte entries).

While in theory it is possible to detect whether or not alignment is
needed by comparing the literal pool size with 512k, in practice this
leads to having two ways of emitting constants, making the code more
complicated.

Prefer code simplicity over trivial size saving, and always group and
align literal pool entries.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118180340.68373-3-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 37 ++++++++++++++++++++++++-------------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5ee1ebc6e448..bb0215d290f4 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/bpf.h>
 #include <linux/mm.h>
+#include <linux/kernel.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
 #include <asm/facility.h>
@@ -39,8 +40,10 @@ struct bpf_jit {
 	int size;		/* Size of program and literal pool */
 	int size_prg;		/* Size of program */
 	int prg;		/* Current position in program */
-	int lit_start;		/* Start of literal pool */
-	int lit;		/* Current position in literal pool */
+	int lit32_start;	/* Start of 32-bit literal pool */
+	int lit32;		/* Current position in 32-bit literal pool */
+	int lit64_start;	/* Start of 64-bit literal pool */
+	int lit64;		/* Current position in 64-bit literal pool */
 	int base_ip;		/* Base address for literal pool */
 	int exit_ip;		/* Address of exit */
 	int r1_thunk_ip;	/* Address of expoline thunk for 'br %r1' */
@@ -287,22 +290,22 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT_CONST_U32(val)					\
 ({								\
 	unsigned int ret;					\
-	ret = jit->lit - jit->base_ip;				\
+	ret = jit->lit32 - jit->base_ip;			\
 	jit->seen |= SEEN_LITERAL;				\
 	if (jit->prg_buf)					\
-		*(u32 *) (jit->prg_buf + jit->lit) = (u32) (val);\
-	jit->lit += 4;						\
+		*(u32 *)(jit->prg_buf + jit->lit32) = (u32)(val);\
+	jit->lit32 += 4;					\
 	ret;							\
 })
 
 #define EMIT_CONST_U64(val)					\
 ({								\
 	unsigned int ret;					\
-	ret = jit->lit - jit->base_ip;				\
+	ret = jit->lit64 - jit->base_ip;			\
 	jit->seen |= SEEN_LITERAL;				\
 	if (jit->prg_buf)					\
-		*(u64 *) (jit->prg_buf + jit->lit) = (u64) (val);\
-	jit->lit += 8;						\
+		*(u64 *)(jit->prg_buf + jit->lit64) = (u64)(val);\
+	jit->lit64 += 8;					\
 	ret;							\
 })
 
@@ -1430,9 +1433,10 @@ static int bpf_set_addr(struct bpf_jit *jit, int i)
 static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
 			bool extra_pass)
 {
-	int i, insn_count;
+	int i, insn_count, lit32_size, lit64_size;
 
-	jit->lit = jit->lit_start;
+	jit->lit32 = jit->lit32_start;
+	jit->lit64 = jit->lit64_start;
 	jit->prg = 0;
 
 	bpf_jit_prologue(jit, fp->aux->stack_depth);
@@ -1448,8 +1452,15 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
 	}
 	bpf_jit_epilogue(jit, fp->aux->stack_depth);
 
-	jit->lit_start = jit->prg;
-	jit->size = jit->lit;
+	lit32_size = jit->lit32 - jit->lit32_start;
+	lit64_size = jit->lit64 - jit->lit64_start;
+	jit->lit32_start = jit->prg;
+	if (lit32_size)
+		jit->lit32_start = ALIGN(jit->lit32_start, 4);
+	jit->lit64_start = jit->lit32_start + lit32_size;
+	if (lit64_size)
+		jit->lit64_start = ALIGN(jit->lit64_start, 8);
+	jit->size = jit->lit64_start + lit64_size;
 	jit->size_prg = jit->prg;
 	return 0;
 }
@@ -1535,7 +1546,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		goto free_addrs;
 	}
 
-	header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 2, jit_fill_hole);
+	header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 8, jit_fill_hole);
 	if (!header) {
 		fp = orig_fp;
 		goto free_addrs;
-- 
cgit v1.2.3


From c1aff5682da2977c26fc087cf6a28e31a430174b Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 18 Nov 2019 19:03:37 +0100
Subject: s390/bpf: Load literal pool register using larl

Currently literal pool register is loaded using basr, which makes it
point not to the beginning of the literal pool, but rather to the next
instruction. In case JITed code is larger than 512k, this renders
literal pool register absolutely useless due to long displacement range
restrictions.

The solution is to use larl to make literal pool register point to the
very beginning of the literal pool. This makes it always possible to
address 512k worth of literal pool entries using long displacement.

However, for short programs, in which the entire literal pool is covered
by basr-generated base, it is still beneficial to use basr, since it is
4 bytes shorter than larl.

Detect situations when basr-generated base does not cover the entire
literal pool, and in such cases use larl instead.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118180340.68373-4-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index bb0215d290f4..964a09fd10f1 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -352,6 +352,15 @@ static bool can_use_rel(struct bpf_jit *jit, int off)
 	return is_valid_rel(off - jit->prg);
 }
 
+/*
+ * Return whether given displacement can be encoded using
+ * Long-Displacement Facility
+ */
+static bool is_valid_ldisp(int disp)
+{
+	return disp >= -524288 && disp <= 524287;
+}
+
 /*
  * Fill whole space with illegal instructions
  */
@@ -476,9 +485,16 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 	save_restore_regs(jit, REGS_SAVE, stack_depth);
 	/* Setup literal pool */
 	if (is_first_pass(jit) || (jit->seen & SEEN_LITERAL)) {
-		/* basr %r13,0 */
-		EMIT2(0x0d00, REG_L, REG_0);
-		jit->base_ip = jit->prg;
+		if (!is_first_pass(jit) &&
+		    is_valid_ldisp(jit->size - (jit->prg + 2))) {
+			/* basr %l,0 */
+			EMIT2(0x0d00, REG_L, REG_0);
+			jit->base_ip = jit->prg;
+		} else {
+			/* larl %l,lit32_start */
+			EMIT6_PCREL_RILB(0xc0000000, REG_L, jit->lit32_start);
+			jit->base_ip = jit->lit32_start;
+		}
 	}
 	/* Setup stack and backchain */
 	if (is_first_pass(jit) || (jit->seen & SEEN_STACK)) {
-- 
cgit v1.2.3


From 451e448ff4bb137da3d4b8b26a8260a2ff66869a Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 18 Nov 2019 19:03:38 +0100
Subject: s390/bpf: Use lgrl instead of lg where possible

lg and lgrl have the same performance characteristics, but the former
requires a base register and is subject to long displacement range
limits, while the latter does not. Therefore, lgrl is totally superior
to lg and should be used instead whenever possible.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118180340.68373-5-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 964a09fd10f1..6b3f85e4c5b0 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -287,28 +287,38 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	REG_SET_SEEN(b1);					\
 })
 
-#define EMIT_CONST_U32(val)					\
+#define _EMIT_CONST_U32(val)					\
 ({								\
 	unsigned int ret;					\
-	ret = jit->lit32 - jit->base_ip;			\
-	jit->seen |= SEEN_LITERAL;				\
+	ret = jit->lit32;					\
 	if (jit->prg_buf)					\
 		*(u32 *)(jit->prg_buf + jit->lit32) = (u32)(val);\
 	jit->lit32 += 4;					\
 	ret;							\
 })
 
-#define EMIT_CONST_U64(val)					\
+#define EMIT_CONST_U32(val)					\
 ({								\
-	unsigned int ret;					\
-	ret = jit->lit64 - jit->base_ip;			\
 	jit->seen |= SEEN_LITERAL;				\
+	_EMIT_CONST_U32(val) - jit->base_ip;			\
+})
+
+#define _EMIT_CONST_U64(val)					\
+({								\
+	unsigned int ret;					\
+	ret = jit->lit64;					\
 	if (jit->prg_buf)					\
 		*(u64 *)(jit->prg_buf + jit->lit64) = (u64)(val);\
 	jit->lit64 += 8;					\
 	ret;							\
 })
 
+#define EMIT_CONST_U64(val)					\
+({								\
+	jit->seen |= SEEN_LITERAL;				\
+	_EMIT_CONST_U64(val) - jit->base_ip;			\
+})
+
 #define EMIT_ZERO(b1)						\
 ({								\
 	if (!fp->aux->verifier_zext) {				\
@@ -612,9 +622,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		u64 imm64;
 
 		imm64 = (u64)(u32) insn[0].imm | ((u64)(u32) insn[1].imm) << 32;
-		/* lg %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm64));
+		/* lgrl %dst,imm */
+		EMIT6_PCREL_RILB(0xc4080000, dst_reg, _EMIT_CONST_U64(imm64));
 		insn_count = 2;
 		break;
 	}
@@ -1086,9 +1095,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 
 		REG_SET_SEEN(BPF_REG_5);
 		jit->seen |= SEEN_FUNC;
-		/* lg %w1,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
-			      EMIT_CONST_U64(func));
+		/* lgrl %w1,func */
+		EMIT6_PCREL_RILB(0xc4080000, REG_W1, _EMIT_CONST_U64(func));
 		if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
 			/* brasl %r14,__s390_indirect_jump_r1 */
 			EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
-- 
cgit v1.2.3


From b25c57b6b7dda3799aaebc5f463776e4a0555927 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 18 Nov 2019 19:03:39 +0100
Subject: s390/bpf: Use lg(f)rl when long displacement cannot be used

If literal pool grows past 524287 mark, it's no longer possible to use
long displacement to reference literal pool entries. In JIT setting
maintaining multiple literal pool registers is next to impossible, since
we operate on one instruction at a time.

Therefore, fall back to loading literal pool entry using PC-relative
addressing, and then using a register-register form of the following
machine instruction.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118180340.68373-6-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 96 +++++++++++++++++++++++++++++++++++++-------
 1 file changed, 81 insertions(+), 15 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 6b3f85e4c5b0..3398cd939496 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -371,6 +371,24 @@ static bool is_valid_ldisp(int disp)
 	return disp >= -524288 && disp <= 524287;
 }
 
+/*
+ * Return whether the next 32-bit literal pool entry can be referenced using
+ * Long-Displacement Facility
+ */
+static bool can_use_ldisp_for_lit32(struct bpf_jit *jit)
+{
+	return is_valid_ldisp(jit->lit32 - jit->base_ip);
+}
+
+/*
+ * Return whether the next 64-bit literal pool entry can be referenced using
+ * Long-Displacement Facility
+ */
+static bool can_use_ldisp_for_lit64(struct bpf_jit *jit)
+{
+	return is_valid_ldisp(jit->lit64 - jit->base_ip);
+}
+
 /*
  * Fill whole space with illegal instructions
  */
@@ -752,9 +770,18 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7080000, REG_W0, 0);
 		/* lr %w1,%dst */
 		EMIT2(0x1800, REG_W1, dst_reg);
-		/* dl %w0,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L,
-			      EMIT_CONST_U32(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit32(jit)) {
+			/* dl %w0,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L,
+				      EMIT_CONST_U32(imm));
+		} else {
+			/* lgfrl %dst,imm */
+			EMIT6_PCREL_RILB(0xc40c0000, dst_reg,
+					 _EMIT_CONST_U32(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* dlr %w0,%dst */
+			EMIT4(0xb9970000, REG_W0, dst_reg);
+		}
 		/* llgfr %dst,%rc */
 		EMIT4(0xb9160000, dst_reg, rc_reg);
 		if (insn_is_zext(&insn[1]))
@@ -776,9 +803,18 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */
 		EMIT4(0xb9040000, REG_W1, dst_reg);
-		/* dlg %w0,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* dlg %w0,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %dst,imm */
+			EMIT6_PCREL_RILB(0xc4080000, dst_reg,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* dlgr %w0,%dst */
+			EMIT4(0xb9870000, REG_W0, dst_reg);
+		}
 		/* lgr %dst,%rc */
 		EMIT4(0xb9040000, dst_reg, rc_reg);
 		break;
@@ -801,9 +837,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT_ZERO(dst_reg);
 		break;
 	case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
-		/* ng %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0080, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* ng %dst,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0080,
+				      dst_reg, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %w0,imm */
+			EMIT6_PCREL_RILB(0xc4080000, REG_W0,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* ngr %dst,%w0 */
+			EMIT4(0xb9800000, dst_reg, REG_W0);
+		}
 		break;
 	/*
 	 * BPF_OR
@@ -823,9 +869,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT_ZERO(dst_reg);
 		break;
 	case BPF_ALU64 | BPF_OR | BPF_K: /* dst = dst | imm */
-		/* og %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0081, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* og %dst,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0081,
+				      dst_reg, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %w0,imm */
+			EMIT6_PCREL_RILB(0xc4080000, REG_W0,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* ogr %dst,%w0 */
+			EMIT4(0xb9810000, dst_reg, REG_W0);
+		}
 		break;
 	/*
 	 * BPF_XOR
@@ -847,9 +903,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT_ZERO(dst_reg);
 		break;
 	case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */
-		/* xg %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0082, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* xg %dst,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0082,
+				      dst_reg, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %w0,imm */
+			EMIT6_PCREL_RILB(0xc4080000, REG_W0,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* xgr %dst,%w0 */
+			EMIT4(0xb9820000, dst_reg, REG_W0);
+		}
 		break;
 	/*
 	 * BPF_LSH
-- 
cgit v1.2.3


From d1242b10ff03a40ae095e6dd54aac4a6f0f547d5 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 18 Nov 2019 19:03:40 +0100
Subject: s390/bpf: Remove JITed image size limitations

Now that jump and long displacement ranges are no longer a problem,
remove the limit on JITed image size. In practice it's still limited by
2G, but with verifier allowing "only" 1M instructions, it's not an
issue.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191118180340.68373-7-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 3398cd939496..8d2134136290 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -52,8 +52,6 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };
 
-#define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
-
 #define SEEN_MEM	BIT(0)		/* use mem[] for temporary storage */
 #define SEEN_LITERAL	BIT(1)		/* code uses literals */
 #define SEEN_FUNC	BIT(2)		/* calls C functions */
@@ -1631,11 +1629,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	/*
 	 * Final pass: Allocate and generate program
 	 */
-	if (jit.size >= BPF_SIZE_MAX) {
-		fp = orig_fp;
-		goto free_addrs;
-	}
-
 	header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 8, jit_fill_hole);
 	if (!header) {
 		fp = orig_fp;
-- 
cgit v1.2.3


From 3de88c9113f88c04abda339f1aa629397bf89e02 Mon Sep 17 00:00:00 2001
From: Luigi Rizzo <lrizzo@google.com>
Date: Mon, 18 Nov 2019 16:19:51 -0800
Subject: net-af_xdp: Use correct number of channels from ethtool

Drivers use different fields to report the number of channels, so take
the maximum of all data channels (rx, tx, combined) when determining the
size of the xsk map. The current code used only 'combined' which was set
to 0 in some drivers e.g. mlx4.

Tested: compiled and run xdpsock -q 3 -r -S on mlx4

Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20191119001951.92930-1-lrizzo@google.com
---
 tools/lib/bpf/xsk.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 303ed633417b..8e0ffa800a71 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -431,13 +431,18 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		goto out;
 	}
 
-	if (err || channels.max_combined == 0)
+	if (err) {
 		/* If the device says it has no channels, then all traffic
 		 * is sent to a single stream, so max queues = 1.
 		 */
 		ret = 1;
-	else
-		ret = channels.max_combined;
+	} else {
+		/* Take the max of rx, tx, combined. Drivers return
+		 * the number of channels in different ways.
+		 */
+		ret = max(channels.max_rx, channels.max_tx);
+		ret = max(ret, (int)channels.max_combined);
+	}
 
 out:
 	close(fd);
-- 
cgit v1.2.3


From a0d7da26ce86a25e97ae191cb90574ada6daea98 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 19 Nov 2019 14:44:47 -0800
Subject: libbpf: Fix call relocation offset calculation bug

When relocating subprogram call, libbpf doesn't take into account
relo->text_off, which comes from symbol's value. This generally works fine for
subprograms implemented as static functions, but breaks for global functions.

Taking a simplified test_pkt_access.c as an example:

__attribute__ ((noinline))
static int test_pkt_access_subprog1(volatile struct __sk_buff *skb)
{
        return skb->len * 2;
}

__attribute__ ((noinline))
static int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb)
{
        return skb->len + val;
}

SEC("classifier/test_pkt_access")
int test_pkt_access(struct __sk_buff *skb)
{
        if (test_pkt_access_subprog1(skb) != skb->len * 2)
                return TC_ACT_SHOT;
        if (test_pkt_access_subprog2(2, skb) != skb->len + 2)
                return TC_ACT_SHOT;
        return TC_ACT_UNSPEC;
}

When compiled, we get two relocations, pointing to '.text' symbol. .text has
st_value set to 0 (it points to the beginning of .text section):

0000000000000008  000000050000000a R_BPF_64_32            0000000000000000 .text
0000000000000040  000000050000000a R_BPF_64_32            0000000000000000 .text

test_pkt_access_subprog1 and test_pkt_access_subprog2 offsets (targets of two
calls) are encoded within call instruction's imm32 part as -1 and 2,
respectively:

0000000000000000 test_pkt_access_subprog1:
       0:       61 10 00 00 00 00 00 00 r0 = *(u32 *)(r1 + 0)
       1:       64 00 00 00 01 00 00 00 w0 <<= 1
       2:       95 00 00 00 00 00 00 00 exit

0000000000000018 test_pkt_access_subprog2:
       3:       61 10 00 00 00 00 00 00 r0 = *(u32 *)(r1 + 0)
       4:       04 00 00 00 02 00 00 00 w0 += 2
       5:       95 00 00 00 00 00 00 00 exit

0000000000000000 test_pkt_access:
       0:       bf 16 00 00 00 00 00 00 r6 = r1
===>   1:       85 10 00 00 ff ff ff ff call -1
       2:       bc 01 00 00 00 00 00 00 w1 = w0
       3:       b4 00 00 00 02 00 00 00 w0 = 2
       4:       61 62 00 00 00 00 00 00 r2 = *(u32 *)(r6 + 0)
       5:       64 02 00 00 01 00 00 00 w2 <<= 1
       6:       5e 21 08 00 00 00 00 00 if w1 != w2 goto +8 <LBB0_3>
       7:       bf 61 00 00 00 00 00 00 r1 = r6
===>   8:       85 10 00 00 02 00 00 00 call 2
       9:       bc 01 00 00 00 00 00 00 w1 = w0
      10:       61 62 00 00 00 00 00 00 r2 = *(u32 *)(r6 + 0)
      11:       04 02 00 00 02 00 00 00 w2 += 2
      12:       b4 00 00 00 ff ff ff ff w0 = -1
      13:       1e 21 01 00 00 00 00 00 if w1 == w2 goto +1 <LBB0_3>
      14:       b4 00 00 00 02 00 00 00 w0 = 2
0000000000000078 LBB0_3:
      15:       95 00 00 00 00 00 00 00 exit

Now, if we compile example with global functions, the setup changes.
Relocations are now against specifically test_pkt_access_subprog1 and
test_pkt_access_subprog2 symbols, with test_pkt_access_subprog2 pointing 24
bytes into its respective section (.text), i.e., 3 instructions in:

0000000000000008  000000070000000a R_BPF_64_32            0000000000000000 test_pkt_access_subprog1
0000000000000048  000000080000000a R_BPF_64_32            0000000000000018 test_pkt_access_subprog2

Calls instructions now encode offsets relative to function symbols and are both
set ot -1:

0000000000000000 test_pkt_access_subprog1:
       0:       61 10 00 00 00 00 00 00 r0 = *(u32 *)(r1 + 0)
       1:       64 00 00 00 01 00 00 00 w0 <<= 1
       2:       95 00 00 00 00 00 00 00 exit

0000000000000018 test_pkt_access_subprog2:
       3:       61 20 00 00 00 00 00 00 r0 = *(u32 *)(r2 + 0)
       4:       0c 10 00 00 00 00 00 00 w0 += w1
       5:       95 00 00 00 00 00 00 00 exit

0000000000000000 test_pkt_access:
       0:       bf 16 00 00 00 00 00 00 r6 = r1
===>   1:       85 10 00 00 ff ff ff ff call -1
       2:       bc 01 00 00 00 00 00 00 w1 = w0
       3:       b4 00 00 00 02 00 00 00 w0 = 2
       4:       61 62 00 00 00 00 00 00 r2 = *(u32 *)(r6 + 0)
       5:       64 02 00 00 01 00 00 00 w2 <<= 1
       6:       5e 21 09 00 00 00 00 00 if w1 != w2 goto +9 <LBB2_3>
       7:       b4 01 00 00 02 00 00 00 w1 = 2
       8:       bf 62 00 00 00 00 00 00 r2 = r6
===>   9:       85 10 00 00 ff ff ff ff call -1
      10:       bc 01 00 00 00 00 00 00 w1 = w0
      11:       61 62 00 00 00 00 00 00 r2 = *(u32 *)(r6 + 0)
      12:       04 02 00 00 02 00 00 00 w2 += 2
      13:       b4 00 00 00 ff ff ff ff w0 = -1
      14:       1e 21 01 00 00 00 00 00 if w1 == w2 goto +1 <LBB2_3>
      15:       b4 00 00 00 02 00 00 00 w0 = 2
0000000000000080 LBB2_3:
      16:       95 00 00 00 00 00 00 00 exit

Thus the right formula to calculate target call offset after relocation should
take into account relocation's target symbol value (offset within section),
call instruction's imm32 offset, and (subtracting, to get relative instruction
offset) instruction index of call instruction itself. All that is shifted by
number of instructions in main program, given all sub-programs are copied over
after main program.

Convert few selftests relying on bpf-to-bpf calls to use global functions
instead of static ones.

Fixes: 48cca7e44f9f ("libbpf: add support for bpf_call")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191119224447.3781271-1-andriin@fb.com
---
 tools/lib/bpf/libbpf.c                             | 8 ++++++--
 tools/testing/selftests/bpf/progs/test_btf_haskv.c | 4 ++--
 tools/testing/selftests/bpf/progs/test_btf_newkv.c | 4 ++--
 tools/testing/selftests/bpf/progs/test_btf_nokv.c  | 4 ++--
 4 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 15e91a1d6c11..a7d183f7ac72 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1870,9 +1870,13 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 				pr_warn("incorrect bpf_call opcode\n");
 				return -LIBBPF_ERRNO__RELOC;
 			}
+			if (sym.st_value % 8) {
+				pr_warn("bad call relo offset: %lu\n", sym.st_value);
+				return -LIBBPF_ERRNO__RELOC;
+			}
 			prog->reloc_desc[i].type = RELO_CALL;
 			prog->reloc_desc[i].insn_idx = insn_idx;
-			prog->reloc_desc[i].text_off = sym.st_value;
+			prog->reloc_desc[i].text_off = sym.st_value / 8;
 			obj->has_pseudo_calls = true;
 			continue;
 		}
@@ -3573,7 +3577,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			 prog->section_name);
 	}
 	insn = &prog->insns[relo->insn_idx];
-	insn->imm += prog->main_prog_cnt - relo->insn_idx;
+	insn->imm += relo->text_off + prog->main_prog_cnt - relo->insn_idx;
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index 763c51447c19..62ad7e22105e 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -26,7 +26,7 @@ struct dummy_tracepoint_args {
 };
 
 __attribute__((noinline))
-static int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -44,7 +44,7 @@ static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 }
 
 __attribute__((noinline))
-static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(struct dummy_tracepoint_args *arg)
 {
 	return test_long_fname_2(arg);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index 96f9e8451029..fb8d91a1dbe0 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -34,7 +34,7 @@ struct dummy_tracepoint_args {
 };
 
 __attribute__((noinline))
-static int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -57,7 +57,7 @@ static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 }
 
 __attribute__((noinline))
-static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(struct dummy_tracepoint_args *arg)
 {
 	return test_long_fname_2(arg);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 434188c37774..3f4422044759 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
@@ -23,7 +23,7 @@ struct dummy_tracepoint_args {
 };
 
 __attribute__((noinline))
-static int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -41,7 +41,7 @@ static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 }
 
 __attribute__((noinline))
-static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(struct dummy_tracepoint_args *arg)
 {
 	return test_long_fname_2(arg);
 }
-- 
cgit v1.2.3


From 24f65050276a4f82d5832e974dabfb5be5c07c39 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 19 Nov 2019 16:25:10 -0800
Subject: selftests/bpf: Enforce no-ALU32 for test_progs-no_alu32

With the most recent Clang, alu32 is enabled by default if -mcpu=probe or
-mcpu=v3 is specified. Use a separate build rule with -mcpu=v2 to enforce no
ALU32 mode.

Suggested-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20191120002510.4130605-1-andriin@fb.com
---
 tools/testing/selftests/bpf/Makefile | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d4400fbe6634..4fe4aec0367c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -163,6 +163,12 @@ define CLANG_BPF_BUILD_RULE
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2
 endef
+# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
+define CLANG_NOALU32_BPF_BUILD_RULE
+	($(CLANG) $3 -O2 -target bpf -emit-llvm				\
+		-c $1 -o - || echo "BPF obj compilation failed") | 	\
+	$(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
+endef
 # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
 define CLANG_NATIVE_BPF_BUILD_RULE
 	($(CLANG) $3 -O2 -emit-llvm					\
@@ -275,6 +281,7 @@ TRUNNER_BPF_LDFLAGS := -mattr=+alu32
 $(eval $(call DEFINE_TEST_RUNNER,test_progs))
 
 # Define test_progs-no_alu32 test runner.
+TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
 TRUNNER_BPF_LDFLAGS :=
 $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
 
-- 
cgit v1.2.3


From b2e2f0e6a6f910c906c083584b6e0afd12266f22 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 19 Nov 2019 22:21:13 +0800
Subject: bpf: Make array_map_mmap static

Fix sparse warning:

kernel/bpf/arraymap.c:481:5: warning:
 symbol 'array_map_mmap' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191119142113.15388-1-yuehaibing@huawei.com
---
 kernel/bpf/arraymap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index a42097c36b0c..633c8c701ff6 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -478,7 +478,7 @@ static int array_map_check_btf(const struct bpf_map *map,
 	return 0;
 }
 
-int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
+static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
-- 
cgit v1.2.3


From 91e6015b082b08a74e5d9d326f651e5890a93519 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 20 Nov 2019 22:38:16 +0100
Subject: bpf: Emit audit messages upon successful prog load and unload

Allow for audit messages to be emitted upon BPF program load and
unload for having a timeline of events. The load itself is in
syscall context, so additional info about the process initiating
the BPF prog creation can be logged and later directly correlated
to the unload event.

The only info really needed from BPF side is the globally unique
prog ID where then audit user space tooling can query / dump all
info needed about the specific BPF program right upon load event
and enrich the record, thus these changes needed here can be kept
small and non-intrusive to the core.

Raw example output:

  # auditctl -D
  # auditctl -a always,exit -F arch=x86_64 -S bpf
  # ausearch --start recent -m 1334
  [...]
  ----
  time->Wed Nov 20 12:45:51 2019
  type=PROCTITLE msg=audit(1574271951.590:8974): proctitle="./test_verifier"
  type=SYSCALL msg=audit(1574271951.590:8974): arch=c000003e syscall=321 success=yes exit=14 a0=5 a1=7ffe2d923e80 a2=78 a3=0 items=0 ppid=742 pid=949 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts0 ses=2 comm="test_verifier" exe="/root/bpf-next/tools/testing/selftests/bpf/test_verifier" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null)
  type=UNKNOWN[1334] msg=audit(1574271951.590:8974): auid=0 uid=0 gid=0 ses=2 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 pid=949 comm="test_verifier" exe="/root/bpf-next/tools/testing/selftests/bpf/test_verifier" prog-id=3260 event=LOAD
  ----
  time->Wed Nov 20 12:45:51 2019
type=UNKNOWN[1334] msg=audit(1574271951.590:8975): prog-id=3260 event=UNLOAD
  ----
  [...]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191120213816.8186-1-jolsa@kernel.org
---
 include/linux/audit.h      |  3 +++
 include/uapi/linux/audit.h |  1 +
 kernel/auditsc.c           |  2 +-
 kernel/bpf/syscall.c       | 31 +++++++++++++++++++++++++++++++
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/include/linux/audit.h b/include/linux/audit.h
index aee3dc9eb378..edd006f4597d 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -159,6 +159,7 @@ extern void		    audit_log_key(struct audit_buffer *ab,
 extern void		    audit_log_link_denied(const char *operation);
 extern void		    audit_log_lost(const char *message);
 
+extern void audit_log_task(struct audit_buffer *ab);
 extern int audit_log_task_context(struct audit_buffer *ab);
 extern void audit_log_task_info(struct audit_buffer *ab);
 
@@ -219,6 +220,8 @@ static inline void audit_log_key(struct audit_buffer *ab, char *key)
 { }
 static inline void audit_log_link_denied(const char *string)
 { }
+static inline void audit_log_task(struct audit_buffer *ab)
+{ }
 static inline int audit_log_task_context(struct audit_buffer *ab)
 {
 	return 0;
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index c89c6495983d..32a5db900f47 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -116,6 +116,7 @@
 #define AUDIT_FANOTIFY		1331	/* Fanotify access decision */
 #define AUDIT_TIME_INJOFFSET	1332	/* Timekeeping offset injected */
 #define AUDIT_TIME_ADJNTPVAL	1333	/* NTP value adjustment */
+#define AUDIT_BPF		1334	/* BPF subsystem */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 4effe01ebbe2..9bf1045fedfa 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2545,7 +2545,7 @@ void __audit_ntp_log(const struct audit_ntp_data *ad)
 	audit_log_ntp_val(ad, "adjust",	AUDIT_NTP_ADJUST);
 }
 
-static void audit_log_task(struct audit_buffer *ab)
+void audit_log_task(struct audit_buffer *ab)
 {
 	kuid_t auid, uid;
 	kgid_t gid;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index bac3becf9f90..17f4254495f2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -23,6 +23,7 @@
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
 #include <linux/nospec.h>
+#include <linux/audit.h>
 #include <uapi/linux/btf.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
@@ -1318,6 +1319,34 @@ static void free_used_maps(struct bpf_prog_aux *aux)
 	kfree(aux->used_maps);
 }
 
+enum bpf_event {
+	BPF_EVENT_LOAD,
+	BPF_EVENT_UNLOAD,
+};
+
+static const char * const bpf_event_audit_str[] = {
+	[BPF_EVENT_LOAD]   = "LOAD",
+	[BPF_EVENT_UNLOAD] = "UNLOAD",
+};
+
+static void bpf_audit_prog(const struct bpf_prog *prog, enum bpf_event event)
+{
+	bool has_task_context = event == BPF_EVENT_LOAD;
+	struct audit_buffer *ab;
+
+	if (audit_enabled == AUDIT_OFF)
+		return;
+	ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_BPF);
+	if (unlikely(!ab))
+		return;
+	if (has_task_context)
+		audit_log_task(ab);
+	audit_log_format(ab, "%sprog-id=%u event=%s",
+			 has_task_context ? " " : "",
+			 prog->aux->id, bpf_event_audit_str[event]);
+	audit_log_end(ab);
+}
+
 int __bpf_prog_charge(struct user_struct *user, u32 pages)
 {
 	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
@@ -1434,6 +1463,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
 	if (atomic64_dec_and_test(&prog->aux->refcnt)) {
 		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
+		bpf_audit_prog(prog, BPF_EVENT_UNLOAD);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
 		__bpf_prog_put_noref(prog, true);
@@ -1843,6 +1873,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	 */
 	bpf_prog_kallsyms_add(prog);
 	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
+	bpf_audit_prog(prog, BPF_EVENT_LOAD);
 
 	err = bpf_prog_new_fd(prog);
 	if (err < 0)
-- 
cgit v1.2.3


From 196e8ca74886c433dcfc64a809707074b936aaf5 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 20 Nov 2019 23:04:44 +0100
Subject: bpf: Switch bpf_map_{area_alloc,area_mmapable_alloc}() to u64 size

Given we recently extended the original bpf_map_area_alloc() helper in
commit fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY"),
we need to apply the same logic as in ff1c08e1f74b ("bpf: Change size
to u64 for bpf_map_{area_alloc, charge_init}()"). To avoid conflicts,
extend it for bpf-next.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h  |  6 +++---
 kernel/bpf/syscall.c | 11 +++++++----
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e913dd5946ae..e89e86122233 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -794,12 +794,12 @@ void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
 void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size);
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
 void bpf_map_charge_finish(struct bpf_map_memory *mem);
 void bpf_map_charge_move(struct bpf_map_memory *dst,
 			 struct bpf_map_memory *src);
-void *bpf_map_area_alloc(size_t size, int numa_node);
-void *bpf_map_area_mmapable_alloc(size_t size, int numa_node);
+void *bpf_map_area_alloc(u64 size, int numa_node);
+void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 17f4254495f2..b51ecb9644d0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -128,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable)
+static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -143,6 +143,9 @@ static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable)
 	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
 
+	if (size >= SIZE_MAX)
+		return NULL;
+
 	/* kmalloc()'ed memory can't be mmap()'ed */
 	if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
 		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
@@ -160,12 +163,12 @@ static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable)
 					   flags, __builtin_return_address(0));
 }
 
-void *bpf_map_area_alloc(size_t size, int numa_node)
+void *bpf_map_area_alloc(u64 size, int numa_node)
 {
 	return __bpf_map_area_alloc(size, numa_node, false);
 }
 
-void *bpf_map_area_mmapable_alloc(size_t size, int numa_node)
+void *bpf_map_area_mmapable_alloc(u64 size, int numa_node)
 {
 	return __bpf_map_area_alloc(size, numa_node, true);
 }
@@ -214,7 +217,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
 		atomic_long_sub(pages, &user->locked_vm);
 }
 
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size)
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
 {
 	u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
 	struct user_struct *user;
-- 
cgit v1.2.3