Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-07-13

The following pull-request contains BPF updates for your *net-next* tree.

We've added 36 non-merge commits during the last 7 day(s) which contain
a total of 62 files changed, 2242 insertions(+), 468 deletions(-).

The main changes are:

1) Avoid trace_printk warning banner by switching bpf_trace_printk to use
   its own tracing event, from Alan.

2) Better libbpf support on older kernels, from Andrii.

3) Additional AF_XDP stats, from Ciara.

4) build time resolution of BTF IDs, from Jiri.

5) BPF_CGROUP_INET_SOCK_RELEASE hook, from Stanislav.
====================

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

Documentation/bpf/btf.rst

@@ -691,6 +691,42 @@ kernel API, the ``insn_off`` is the instruction offset in the unit of ``struct
 bpf_insn``. For ELF API, the ``insn_off`` is the byte offset from the
 beginning of section (``btf_ext_info_sec->sec_name_off``).
 
+4.2 .BTF_ids section
+====================
+
+The .BTF_ids section encodes BTF ID values that are used within the kernel.
+
+This section is created during the kernel compilation with the help of
+macros defined in ``include/linux/btf_ids.h`` header file. Kernel code can
+use them to create lists and sets (sorted lists) of BTF ID values.
+
+The ``BTF_ID_LIST`` and ``BTF_ID`` macros define unsorted list of BTF ID values,
+with following syntax::
+
+  BTF_ID_LIST(list)
+  BTF_ID(type1, name1)
+  BTF_ID(type2, name2)
+
+resulting in following layout in .BTF_ids section::
+
+  __BTF_ID__type1__name1__1:
+  .zero 4
+  __BTF_ID__type2__name2__2:
+  .zero 4
+
+The ``u32 list[];`` variable is defined to access the list.
+
+The ``BTF_ID_UNUSED`` macro defines 4 zero bytes. It's used when we
+want to define unused entry in BTF_ID_LIST, like::
+
+      BTF_ID_LIST(bpf_skb_output_btf_ids)
+      BTF_ID(struct, sk_buff)
+      BTF_ID_UNUSED
+      BTF_ID(struct, task_struct)
+
+All the BTF ID lists and sets are compiled in the .BTF_ids section and
+resolved during the linking phase of kernel build by ``resolve_btfids`` tool.
+
 5. Using BTF
 ************
 

Makefile

@@ -448,6 +448,7 @@ OBJSIZE		= $(CROSS_COMPILE)size
 STRIP		= $(CROSS_COMPILE)strip
 endif
 PAHOLE		= pahole
+RESOLVE_BTFIDS	= $(objtree)/tools/bpf/resolve_btfids/resolve_btfids
 LEX		= flex
 YACC		= bison
 AWK		= awk
@@ -510,7 +511,7 @@ GCC_PLUGINS_CFLAGS :=
 CLANG_FLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE LEX YACC AWK INSTALLKERNEL
+export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
 export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
 export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ
 export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
@@ -1053,9 +1054,10 @@ export mod_sign_cmd
 
 HOST_LIBELF_LIBS = $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
 
+has_libelf = $(call try-run,\
+               echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0)
+
 ifdef CONFIG_STACK_VALIDATION
-  has_libelf := $(call try-run,\
-		echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0)
   ifeq ($(has_libelf),1)
     objtool_target := tools/objtool FORCE
   else
@@ -1064,6 +1066,14 @@ ifdef CONFIG_STACK_VALIDATION
   endif
 endif
 
+ifdef CONFIG_DEBUG_INFO_BTF
+  ifeq ($(has_libelf),1)
+    resolve_btfids_target := tools/bpf/resolve_btfids FORCE
+  else
+    ERROR_RESOLVE_BTFIDS := 1
+  endif
+endif
+
 PHONY += prepare0
 
 export MODORDER := $(extmod-prefix)modules.order
@@ -1175,7 +1185,7 @@ prepare0: archprepare
 	$(Q)$(MAKE) $(build)=.
 
 # All the preparing..
-prepare: prepare0 prepare-objtool
+prepare: prepare0 prepare-objtool prepare-resolve_btfids
 
 # Support for using generic headers in asm-generic
 asm-generic := -f $(srctree)/scripts/Makefile.asm-generic obj
@@ -1188,7 +1198,7 @@ uapi-asm-generic:
 	$(Q)$(MAKE) $(asm-generic)=arch/$(SRCARCH)/include/generated/uapi/asm \
 	generic=include/uapi/asm-generic
 
-PHONY += prepare-objtool
+PHONY += prepare-objtool prepare-resolve_btfids
 prepare-objtool: $(objtool_target)
 ifeq ($(SKIP_STACK_VALIDATION),1)
 ifdef CONFIG_UNWINDER_ORC
@@ -1199,6 +1209,11 @@ else
 endif
 endif
 
+prepare-resolve_btfids: $(resolve_btfids_target)
+ifeq ($(ERROR_RESOLVE_BTFIDS),1)
+	@echo "error: Cannot resolve BTF IDs for CONFIG_DEBUG_INFO_BTF, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2
+	@false
+endif
 # Generate some files
 # ---------------------------------------------------------------------------
 

include/asm-generic/vmlinux.lds.h

@@ -641,6 +641,10 @@
 		__start_BTF = .;					\
 		*(.BTF)							\
 		__stop_BTF = .;						\
+	}								\
+	. = ALIGN(4);							\
+	.BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) {			\
+		*(.BTF_ids)						\
 	}
 #else
 #define BTF

include/linux/bpf-cgroup.h

@@ -210,6 +210,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk)				       \
 	BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE)
 
+#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk)			       \
+	BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_RELEASE)
+
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk)				       \
 	BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND)
 
@@ -401,6 +404,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })

include/linux/btf_ids.h

@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_BTF_IDS_H
+#define _LINUX_BTF_IDS_H
+
+#include <linux/compiler.h> /* for __PASTE */
+
+/*
+ * Following macros help to define lists of BTF IDs placed
+ * in .BTF_ids section. They are initially filled with zeros
+ * (during compilation) and resolved later during the
+ * linking phase by resolve_btfids tool.
+ *
+ * Any change in list layout must be reflected in resolve_btfids
+ * tool logic.
+ */
+
+#define BTF_IDS_SECTION ".BTF_ids"
+
+#define ____BTF_ID(symbol)				\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+".local " #symbol " ;                          \n"	\
+".type  " #symbol ", @object;                  \n"	\
+".size  " #symbol ", 4;                        \n"	\
+#symbol ":                                     \n"	\
+".zero 4                                       \n"	\
+".popsection;                                  \n");
+
+#define __BTF_ID(symbol) \
+	____BTF_ID(symbol)
+
+#define __ID(prefix) \
+	__PASTE(prefix, __COUNTER__)
+
+/*
+ * The BTF_ID defines unique symbol for each ID pointing
+ * to 4 zero bytes.
+ */
+#define BTF_ID(prefix, name) \
+	__BTF_ID(__ID(__BTF_ID__##prefix##__##name##__))
+
+/*
+ * The BTF_ID_LIST macro defines pure (unsorted) list
+ * of BTF IDs, with following layout:
+ *
+ * BTF_ID_LIST(list1)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ *
+ * list1:
+ * __BTF_ID__type1__name1__1:
+ * .zero 4
+ * __BTF_ID__type2__name2__2:
+ * .zero 4
+ *
+ */
+#define __BTF_ID_LIST(name)				\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+".local " #name ";                             \n"	\
+#name ":;                                      \n"	\
+".popsection;                                  \n");	\
+
+#define BTF_ID_LIST(name)				\
+__BTF_ID_LIST(name)					\
+extern u32 name[];
+
+/*
+ * The BTF_ID_UNUSED macro defines 4 zero bytes.
+ * It's used when we want to define 'unused' entry
+ * in BTF_ID_LIST, like:
+ *
+ *   BTF_ID_LIST(bpf_skb_output_btf_ids)
+ *   BTF_ID(struct, sk_buff)
+ *   BTF_ID_UNUSED
+ *   BTF_ID(struct, task_struct)
+ */
+
+#define BTF_ID_UNUSED					\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+".zero 4                                       \n"	\
+".popsection;                                  \n");
+
+
+#endif

include/net/xdp_sock.h

@@ -69,7 +69,11 @@ struct xdp_sock {
 	spinlock_t tx_completion_lock;
 	/* Protects generic receive. */
 	spinlock_t rx_lock;
+
+	/* Statistics */
 	u64 rx_dropped;
+	u64 rx_queue_full;
+
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;

include/uapi/linux/bpf.h

@@ -226,6 +226,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
+	BPF_CGROUP_INET_SOCK_RELEASE,
 	__MAX_BPF_ATTACH_TYPE
 };
 

include/uapi/linux/if_xdp.h

@@ -73,9 +73,12 @@ struct xdp_umem_reg {
 };
 
 struct xdp_statistics {
-	__u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+	__u64 rx_dropped; /* Dropped for other reasons */
 	__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+	__u64 rx_ring_full; /* Dropped due to rx ring being full */
+	__u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */
+	__u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */
 };
 
 struct xdp_options {

include/uapi/linux/xdp_diag.h

@@ -30,6 +30,7 @@ struct xdp_diag_msg {
 #define XDP_SHOW_RING_CFG	(1 << 1)
 #define XDP_SHOW_UMEM		(1 << 2)
 #define XDP_SHOW_MEMINFO	(1 << 3)
+#define XDP_SHOW_STATS		(1 << 4)
 
 enum {
 	XDP_DIAG_NONE,
@@ -41,6 +42,7 @@ enum {
 	XDP_DIAG_UMEM_FILL_RING,
 	XDP_DIAG_UMEM_COMPLETION_RING,
 	XDP_DIAG_MEMINFO,
+	XDP_DIAG_STATS,
 	__XDP_DIAG_MAX,
 };
 
@@ -69,4 +71,13 @@ struct xdp_diag_umem {
 	__u32	refs;
 };
 
+struct xdp_diag_stats {
+	__u64	n_rx_dropped;
+	__u64	n_rx_invalid;
+	__u64	n_rx_full;
+	__u64	n_fill_ring_empty;
+	__u64	n_tx_invalid;
+	__u64	n_tx_ring_empty;
+};
+
 #endif /* _LINUX_XDP_DIAG_H */

kernel/bpf/btf.c

@@ -18,6 +18,7 @@
 #include <linux/sort.h>
 #include <linux/bpf_verifier.h>
 #include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include <linux/skmsg.h>
 #include <linux/perf_event.h>
 #include <net/sock.h>
@@ -3621,12 +3622,15 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 	return kern_ctx_type->type;
 }
 
+BTF_ID_LIST(bpf_ctx_convert_btf_id)
+BTF_ID(struct, bpf_ctx_convert)
+
 struct btf *btf_parse_vmlinux(void)
 {
 	struct btf_verifier_env *env = NULL;
 	struct bpf_verifier_log *log;
 	struct btf *btf = NULL;
-	int err, btf_id;
+	int err;
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
 	if (!env)
@@ -3659,14 +3663,8 @@ struct btf *btf_parse_vmlinux(void)
 	if (err)
 		goto errout;
 
-	/* find struct bpf_ctx_convert for type checking later */
-	btf_id = btf_find_by_name_kind(btf, "bpf_ctx_convert", BTF_KIND_STRUCT);
-	if (btf_id < 0) {
-		err = btf_id;
-		goto errout;
-	}
 	/* btf_parse_vmlinux() runs under bpf_verifier_lock */
-	bpf_ctx_convert.t = btf_type_by_id(btf, btf_id);
+	bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]);
 
 	/* find bpf map structs for map_ptr access checking */
 	err = btf_vmlinux_map_ids_init(btf, log);
@@ -4079,96 +4077,17 @@ error:
 	return -EINVAL;
 }
 
-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;
-	const struct btf_type *t;
-	const char *tname, *sym;
-	u32 btf_id, i;
-
-	if (IS_ERR(btf_vmlinux)) {
-		bpf_log(log, "btf_vmlinux is malformed\n");
-		return -EINVAL;
-	}
-
-	sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4);
-	if (!sym) {
-		bpf_log(log, "kernel doesn't have kallsyms\n");
-		return -EFAULT;
-	}
-
-	for (i = 1; i <= btf_vmlinux->nr_types; i++) {
-		t = btf_type_by_id(btf_vmlinux, i);
-		if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF)
-			continue;
-		tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
-		if (!strcmp(tname, fnname))
-			break;
-	}
-	if (i > btf_vmlinux->nr_types) {
-		bpf_log(log, "helper %s type is not found\n", fnname);
-		return -ENOENT;
-	}
-
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	if (!btf_type_is_ptr(t))
-		return -EFAULT;
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	if (!btf_type_is_func_proto(t))
-		return -EFAULT;
-
-	args = (const struct btf_param *)(t + 1);
-	if (arg >= btf_type_vlen(t)) {
-		bpf_log(log, "bpf helper %s doesn't have %d-th argument\n",
-			fnname, arg);
-		return -EINVAL;
-	}
-
-	t = btf_type_by_id(btf_vmlinux, args[arg].type);
-	if (!btf_type_is_ptr(t) || !t->type) {
-		/* anything but the pointer to struct is a helper config bug */
-		bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n");
-		return -EFAULT;
-	}
-	btf_id = t->type;
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	/* skip modifiers */
-	while (btf_type_is_modifier(t)) {
-		btf_id = t->type;
-		t = btf_type_by_id(btf_vmlinux, t->type);
-	}
-	if (!btf_type_is_struct(t)) {
-		bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n");
-		return -EFAULT;
-	}
-	bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4,
-		arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off));
-	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;
+	int id;
 
 	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;
+	id = fn->btf_id[arg];
+	if (!id || id > btf_vmlinux->nr_types)
+		return -EINVAL;
+	return id;
 }
 
 static int __get_type_size(struct btf *btf, u32 btf_id,

kernel/bpf/stackmap.c

@@ -9,6 +9,7 @@
 #include <linux/elf.h>
 #include <linux/pagemap.h>
 #include <linux/irq_work.h>
+#include <linux/btf_ids.h>
 #include "percpu_freelist.h"
 
 #define STACK_CREATE_FLAG_MASK					\
@@ -576,7 +577,9 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	return __bpf_get_stack(regs, task, buf, size, flags);
 }
 
-static int bpf_get_task_stack_btf_ids[5];
+BTF_ID_LIST(bpf_get_task_stack_btf_ids)
+BTF_ID(struct, task_struct)
+
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,

kernel/bpf/syscall.c

@@ -1981,6 +1981,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 		switch (expected_attach_type) {
 		case BPF_CGROUP_INET_SOCK_CREATE:
+		case BPF_CGROUP_INET_SOCK_RELEASE:
 		case BPF_CGROUP_INET4_POST_BIND:
 		case BPF_CGROUP_INET6_POST_BIND:
 			return 0;
@@ -2779,6 +2780,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_CGROUP_SKB;
 		break;
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
 	case BPF_CGROUP_INET4_POST_BIND:
 	case BPF_CGROUP_INET6_POST_BIND:
 		return BPF_PROG_TYPE_CGROUP_SOCK;
@@ -2927,6 +2929,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_POST_BIND:

kernel/trace/Makefile

@@ -31,6 +31,8 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
 GCOV_PROFILE := y
 endif
 
+CFLAGS_bpf_trace.o := -I$(src)
+
 CFLAGS_trace_benchmark.o := -I$(src)
 CFLAGS_trace_events_filter.o := -I$(src)
 

kernel/trace/bpf_trace.c

@@ -11,14 +11,19 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/kprobes.h>
+#include <linux/spinlock.h>
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
+#include <linux/btf_ids.h>
 
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
 #include "trace.h"
 
+#define CREATE_TRACE_POINTS
+#include "bpf_trace.h"
+
 #define bpf_event_rcu_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
 
@@ -374,6 +379,30 @@ static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
 	}
 }
 
+static DEFINE_RAW_SPINLOCK(trace_printk_lock);
+
+#define BPF_TRACE_PRINTK_SIZE   1024
+
+static inline __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	va_list ap;
+	int ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	va_start(ap, fmt);
+	ret = vsnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+	/* vsnprintf() will not append null for zero-length strings */
+	if (ret == 0)
+		buf[0] = '\0';
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	return ret;
+}
+
 /*
  * Only limited trace_printk() conversion specifiers allowed:
  * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
@@ -483,8 +512,7 @@ fmt_next:
  */
 #define __BPF_TP_EMIT()	__BPF_ARG3_TP()
 #define __BPF_TP(...)							\
-	__trace_printk(0 /* Fake ip */,					\
-		       fmt, ##__VA_ARGS__)
+	bpf_do_trace_printk(fmt, ##__VA_ARGS__)
 
 #define __BPF_ARG1_TP(...)						\
 	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
@@ -521,10 +549,15 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 {
 	/*
-	 * this program might be calling bpf_trace_printk,
-	 * so allocate per-cpu printk buffers
+	 * This program might be calling bpf_trace_printk,
+	 * so enable the associated bpf_trace/bpf_trace_printk event.
+	 * Repeat this each time as it is possible a user has
+	 * disabled bpf_trace_printk events.  By loading a program
+	 * calling bpf_trace_printk() however the user has expressed
+	 * the intent to see such events.
 	 */
-	trace_printk_init_buffers();
+	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
+		pr_warn_ratelimited("could not enable bpf_trace_printk events");
 
 	return &bpf_trace_printk_proto;
 }
@@ -710,7 +743,9 @@ out:
 	return err;
 }
 
-static int bpf_seq_printf_btf_ids[5];
+BTF_ID_LIST(bpf_seq_printf_btf_ids)
+BTF_ID(struct, seq_file)
+
 static const struct bpf_func_proto bpf_seq_printf_proto = {
 	.func		= bpf_seq_printf,
 	.gpl_only	= true,
@@ -728,7 +763,9 @@ BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
 	return seq_write(m, data, len) ? -EOVERFLOW : 0;
 }
 
-static int bpf_seq_write_btf_ids[5];
+BTF_ID_LIST(bpf_seq_write_btf_ids)
+BTF_ID(struct, seq_file)
+
 static const struct bpf_func_proto bpf_seq_write_proto = {
 	.func		= bpf_seq_write,
 	.gpl_only	= true,

kernel/trace/bpf_trace.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_trace
+
+#if !defined(_TRACE_BPF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_BPF_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(bpf_trace_printk,
+
+	TP_PROTO(const char *bpf_string),
+
+	TP_ARGS(bpf_string),
+
+	TP_STRUCT__entry(
+		__string(bpf_string, bpf_string)
+	),
+
+	TP_fast_assign(
+		__assign_str(bpf_string, bpf_string);
+	),
+
+	TP_printk("%s", __get_str(bpf_string))
+);
+
+#endif /* _TRACE_BPF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_trace
+
+#include <trace/define_trace.h>

net/core/filter.c

@@ -75,6 +75,7 @@
 #include <net/ipv6_stubs.h>
 #include <net/bpf_sk_storage.h>
 #include <net/transp_v6.h>
+#include <linux/btf_ids.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -3779,7 +3780,9 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-static int bpf_skb_output_btf_ids[5];
+BTF_ID_LIST(bpf_skb_output_btf_ids)
+BTF_ID(struct, sk_buff)
+
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
@@ -4173,7 +4176,9 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-static int bpf_xdp_output_btf_ids[5];
+BTF_ID_LIST(bpf_xdp_output_btf_ids)
+BTF_ID(struct, xdp_buff)
+
 const struct bpf_func_proto bpf_xdp_output_proto = {
 	.func		= bpf_xdp_event_output,
 	.gpl_only	= true,
@@ -6894,6 +6899,7 @@ static bool __sock_filter_check_attach_type(int off,
 	case offsetof(struct bpf_sock, priority):
 		switch (attach_type) {
 		case BPF_CGROUP_INET_SOCK_CREATE:
+		case BPF_CGROUP_INET_SOCK_RELEASE:
 			goto full_access;
 		default:
 			return false;

net/ipv4/af_inet.c

@@ -411,6 +411,9 @@ int inet_release(struct socket *sock)
 	if (sk) {
 		long timeout;
 
+		if (!sk->sk_kern_sock)
+			BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk);
+
 		/* Applications forget to leave groups before exiting */
 		ip_mc_drop_socket(sk);
 

net/xdp/xsk.c

@@ -123,7 +123,7 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	addr = xp_get_handle(xskb);
 	err = xskq_prod_reserve_desc(xs->rx, addr, len);
 	if (err) {
-		xs->rx_dropped++;
+		xs->rx_queue_full++;
 		return err;
 	}
 
@@ -274,8 +274,10 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
-		if (!xskq_cons_peek_desc(xs->tx, desc, umem))
+		if (!xskq_cons_peek_desc(xs->tx, desc, umem)) {
+			xs->tx->queue_empty_descs++;
 			continue;
+		}
 
 		/* This is the backpressure mechanism for the Tx path.
 		 * Reserve space in the completion queue and only proceed
@@ -387,6 +389,8 @@ static int xsk_generic_xmit(struct sock *sk)
 		sent_frame = true;
 	}
 
+	xs->tx->queue_empty_descs++;
+
 out:
 	if (sent_frame)
 		sk->sk_write_space(sk);
@@ -812,6 +816,12 @@ static void xsk_enter_umem_offsets(struct xdp_ring_offset_v1 *ring)
 	ring->desc = offsetof(struct xdp_umem_ring, desc);
 }
 
+struct xdp_statistics_v1 {
+	__u64 rx_dropped;
+	__u64 rx_invalid_descs;
+	__u64 tx_invalid_descs;
+};
+
 static int xsk_getsockopt(struct socket *sock, int level, int optname,
 			  char __user *optval, int __user *optlen)
 {
@@ -831,19 +841,35 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
 	case XDP_STATISTICS:
 	{
 		struct xdp_statistics stats;
+		bool extra_stats = true;
+		size_t stats_size;
 
-		if (len < sizeof(stats))
+		if (len < sizeof(struct xdp_statistics_v1)) {
 			return -EINVAL;
+		} else if (len < sizeof(stats)) {
+			extra_stats = false;
+			stats_size = sizeof(struct xdp_statistics_v1);
+		} else {
+			stats_size = sizeof(stats);
+		}
 
 		mutex_lock(&xs->mutex);
 		stats.rx_dropped = xs->rx_dropped;
+		if (extra_stats) {
+			stats.rx_ring_full = xs->rx_queue_full;
+			stats.rx_fill_ring_empty_descs =
+				xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+			stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx);
+		} else {
+			stats.rx_dropped += xs->rx_queue_full;
+		}
 		stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx);
 		stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx);
 		mutex_unlock(&xs->mutex);
 
-		if (copy_to_user(optval, &stats, sizeof(stats)))
+		if (copy_to_user(optval, &stats, stats_size))
 			return -EFAULT;
-		if (put_user(sizeof(stats), optlen))
+		if (put_user(stats_size, optlen))
 			return -EFAULT;
 
 		return 0;

net/xdp/xsk_buff_pool.c

@@ -189,6 +189,7 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
 
 	for (;;) {
 		if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) {
+			pool->fq->queue_empty_descs++;
 			xp_release(xskb);
 			return NULL;
 		}

net/xdp/xsk_diag.c

@@ -76,6 +76,19 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 	return err;
 }
 
+static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb)
+{
+	struct xdp_diag_stats du = {};
+
+	du.n_rx_dropped = xs->rx_dropped;
+	du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx);
+	du.n_rx_full = xs->rx_queue_full;
+	du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+	du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx);
+	du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx);
+	return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du);
+}
+
 static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
 			 struct xdp_diag_req *req,
 			 struct user_namespace *user_ns,
@@ -118,6 +131,10 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
 	    sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
+	if ((req->xdiag_show & XDP_SHOW_STATS) &&
+	    xsk_diag_put_stats(xs, nlskb))
+		goto out_nlmsg_trim;
+
 	mutex_unlock(&xs->mutex);
 	nlmsg_end(nlskb, nlh);
 	return 0;