Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-03-25

We've added 38 non-merge commits during the last 13 day(s) which contain
a total of 50 files changed, 867 insertions(+), 274 deletions(-).

The main changes are:

1) Add the ability to specify and retrieve BPF cookie also for raw
   tracepoint programs in order to ease migration from classic to raw
   tracepoints, from Andrii Nakryiko.

2) Allow the use of bpf_get_{ns_,}current_pid_tgid() helper for all
   program types and add additional BPF selftests, from Yonghong Song.

3) Several improvements to bpftool and its build, for example, enabling
   libbpf logs when loading pid_iter in debug mode, from Quentin Monnet.

4) Check the return code of all BPF-related set_memory_*() functions during
   load and bail out in case they fail, from Christophe Leroy.

5) Avoid a goto in regs_refine_cond_op() such that the verifier can
   be better integrated into Agni tool which doesn't support backedges
   yet, from Harishankar Vishwanathan.

6) Add a small BPF trie perf improvement by always inlining
   longest_prefix_match, from Jesper Dangaard Brouer.

7) Small BPF selftest refactor in bpf_tcp_ca.c to utilize start_server()
   helper instead of open-coding it, from Geliang Tang.

8) Improve test_tc_tunnel.sh BPF selftest to prevent client connect
   before the server bind, from Alessandro Carminati.

9) Fix BPF selftest benchmark for older glibc and use syscall(SYS_gettid)
   instead of gettid(), from Alan Maguire.

10) Implement a backward-compatible method for struct_ops types with
    additional fields which are not present in older kernels,
    from Kui-Feng Lee.

11) Add a small helper to check if an instruction is addr_space_cast
    from as(0) to as(1) and utilize it in x86-64 JIT, from Puranjay Mohan.

12) Small cleanup to remove unnecessary error check in
    bpf_struct_ops_map_update_elem, from Martin KaFai Lau.

13) Improvements to libbpf fd validity checks for BPF map/programs,
    from Mykyta Yatsenko.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (38 commits)
  selftests/bpf: Fix flaky test btf_map_in_map/lookup_update
  bpf: implement insn_is_cast_user() helper for JITs
  bpf: Avoid get_kernel_nofault() to fetch kprobe entry IP
  selftests/bpf: Use start_server in bpf_tcp_ca
  bpf: Sync uapi bpf.h to tools directory
  libbpf: Add new sec_def "sk_skb/verdict"
  selftests/bpf: Mark uprobe trigger functions with nocf_check attribute
  selftests/bpf: Use syscall(SYS_gettid) instead of gettid() wrapper in bench
  bpf-next: Avoid goto in regs_refine_cond_op()
  bpftool: Clean up HOST_CFLAGS, HOST_LDFLAGS for bootstrap bpftool
  selftests/bpf: scale benchmark counting by using per-CPU counters
  bpftool: Remove unnecessary source files from bootstrap version
  bpftool: Enable libbpf logs when loading pid_iter in debug mode
  selftests/bpf: add raw_tp/tp_btf BPF cookie subtests
  libbpf: add support for BPF cookie for raw_tp/tp_btf programs
  bpf: support BPF cookie in raw tracepoint (raw_tp, tp_btf) programs
  bpf: pass whole link instead of prog when triggering raw tracepoint
  bpf: flatten bpf_probe_register call chain
  selftests/bpf: Prevent client connect before server bind in test_tc_tunnel.sh
  selftests/bpf: Add a sk_msg prog bpf_get_ns_current_pid_tgid() test
  ...
====================

Link: https://lore.kernel.org/r/20240325233940.7154-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

arch/arm/net/bpf_jit_32.c

@@ -2222,28 +2222,21 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* If building the body of the JITed code fails somehow,
 	 * we fall back to the interpretation.
 	 */
-	if (build_body(&ctx) < 0) {
-		image_ptr = NULL;
-		bpf_jit_binary_free(header);
-		prog = orig_prog;
-		goto out_imms;
-	}
+	if (build_body(&ctx) < 0)
+		goto out_free;
 	build_epilogue(&ctx);
 
 	/* 3.) Extra pass to validate JITed Code */
-	if (validate_code(&ctx)) {
-		image_ptr = NULL;
-		bpf_jit_binary_free(header);
-		prog = orig_prog;
-		goto out_imms;
-	}
+	if (validate_code(&ctx))
+		goto out_free;
 	flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx));
 
 	if (bpf_jit_enable > 1)
 		/* there are 2 passes here */
 		bpf_jit_dump(prog->len, image_size, 2, ctx.target);
 
-	bpf_jit_binary_lock_ro(header);
+	if (bpf_jit_binary_lock_ro(header))
+		goto out_free;
 	prog->bpf_func = (void *)ctx.target;
 	prog->jited = 1;
 	prog->jited_len = image_size;
@@ -2260,5 +2253,11 @@ out:
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
 					   tmp : orig_prog);
 	return prog;
+
+out_free:
+	image_ptr = NULL;
+	bpf_jit_binary_free(header);
+	prog = orig_prog;
+	goto out_imms;
 }
 

arch/arm64/net/bpf_jit_comp.c

@@ -2176,12 +2176,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size)
 	bpf_prog_pack_free(image, size);
 }
 
-void arch_protect_bpf_trampoline(void *image, unsigned int size)
-{
-}
-
-void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
 {
+	return 0;
 }
 
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,

arch/loongarch/net/bpf_jit.c

@@ -1294,16 +1294,19 @@ skip_init_ctx:
 	flush_icache_range((unsigned long)header, (unsigned long)(ctx.image + ctx.idx));
 
 	if (!prog->is_func || extra_pass) {
+		int err;
+
 		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
 			pr_err_once("multi-func JIT bug %d != %d\n",
 				    ctx.idx, jit_data->ctx.idx);
-			bpf_jit_binary_free(header);
-			prog->bpf_func = NULL;
-			prog->jited = 0;
-			prog->jited_len = 0;
-			goto out_offset;
+			goto out_free;
+		}
+		err = bpf_jit_binary_lock_ro(header);
+		if (err) {
+			pr_err_once("bpf_jit_binary_lock_ro() returned %d\n",
+				    err);
+			goto out_free;
 		}
-		bpf_jit_binary_lock_ro(header);
 	} else {
 		jit_data->ctx = ctx;
 		jit_data->image = image_ptr;
@@ -1334,6 +1337,13 @@ out:
 	out_offset = -1;
 
 	return prog;
+
+out_free:
+	bpf_jit_binary_free(header);
+	prog->bpf_func = NULL;
+	prog->jited = 0;
+	prog->jited_len = 0;
+	goto out_offset;
 }
 
 /* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */

arch/mips/net/bpf_jit_comp.c

@@ -1012,7 +1012,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	bpf_prog_fill_jited_linfo(prog, &ctx.descriptors[1]);
 
 	/* Set as read-only exec and flush instruction cache */
-	bpf_jit_binary_lock_ro(header);
+	if (bpf_jit_binary_lock_ro(header))
+		goto out_err;
 	flush_icache_range((unsigned long)header,
 			   (unsigned long)&ctx.target[ctx.jit_index]);
 

arch/parisc/net/bpf_jit_core.c

@@ -167,7 +167,13 @@ skip_init_ctx:
 	bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
 
 	if (!prog->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(jit_data->header);
+		if (bpf_jit_binary_lock_ro(jit_data->header)) {
+			bpf_jit_binary_free(jit_data->header);
+			prog->bpf_func = NULL;
+			prog->jited = 0;
+			prog->jited_len = 0;
+			goto out_offset;
+		}
 		prologue_len = ctx->epilogue_offset - ctx->body_len;
 		for (i = 0; i < prog->len; i++)
 			ctx->offset[i] += prologue_len;

arch/s390/net/bpf_jit_comp.c

@@ -2111,7 +2111,11 @@ skip_init_ctx:
 		print_fn_code(jit.prg_buf, jit.size_prg);
 	}
 	if (!fp->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(header);
+		if (bpf_jit_binary_lock_ro(header)) {
+			bpf_jit_binary_free(header);
+			fp = orig_fp;
+			goto free_addrs;
+		}
 	} else {
 		jit_data->header = header;
 		jit_data->ctx = jit;

arch/sparc/net/bpf_jit_comp_64.c

@@ -1602,7 +1602,11 @@ skip_init_ctx:
 	bpf_flush_icache(header, (u8 *)header + header->size);
 
 	if (!prog->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(header);
+		if (bpf_jit_binary_lock_ro(header)) {
+			bpf_jit_binary_free(header);
+			prog = orig_prog;
+			goto out_off;
+		}
 	} else {
 		jit_data->ctx = ctx;
 		jit_data->image = image_ptr;

arch/x86/net/bpf_jit_comp.c

@@ -1351,8 +1351,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 			break;
 
 		case BPF_ALU64 | BPF_MOV | BPF_X:
-			if (insn->off == BPF_ADDR_SPACE_CAST &&
-			    insn->imm == 1U << 16) {
+			if (insn_is_cast_user(insn)) {
 				if (dst_reg != src_reg)
 					/* 32-bit mov */
 					emit_mov_reg(&prog, false, dst_reg, src_reg);
@@ -3004,12 +3003,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size)
 	bpf_prog_pack_free(image, size);
 }
 
-void arch_protect_bpf_trampoline(void *image, unsigned int size)
-{
-}
-
-void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
 {
+	return 0;
 }
 
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,

arch/x86/net/bpf_jit_comp32.c

@@ -2600,8 +2600,7 @@ out_image:
 	if (bpf_jit_enable > 1)
 		bpf_jit_dump(prog->len, proglen, pass + 1, image);
 
-	if (image) {
-		bpf_jit_binary_lock_ro(header);
+	if (image && !bpf_jit_binary_lock_ro(header)) {
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
 		prog->jited_len = proglen;

include/linux/bpf.h

@@ -1116,8 +1116,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				void *func_addr);
 void *arch_alloc_bpf_trampoline(unsigned int size);
 void arch_free_bpf_trampoline(void *image, unsigned int size);
-void arch_protect_bpf_trampoline(void *image, unsigned int size);
-void arch_unprotect_bpf_trampoline(void *image, unsigned int size);
+int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size);
 int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 			     struct bpf_tramp_links *tlinks, void *func_addr);
 
@@ -1608,6 +1607,12 @@ struct bpf_tracing_link {
 	struct bpf_prog *tgt_prog;
 };
 
+struct bpf_raw_tp_link {
+	struct bpf_link link;
+	struct bpf_raw_event_map *btp;
+	u64 cookie;
+};
+
 struct bpf_link_primer {
 	struct bpf_link *link;
 	struct file *file;

include/linux/filter.h

@@ -228,6 +228,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 	return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1;
 }
 
+/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers
+ * to pointers in user vma.
+ */
+static inline bool insn_is_cast_user(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) &&
+			      insn->off == BPF_ADDR_SPACE_CAST &&
+			      insn->imm == 1U << 16;
+}
+
 /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
 #define BPF_LD_IMM64(DST, IMM)					\
 	BPF_LD_IMM64_RAW(DST, 0, IMM)
@@ -887,20 +897,22 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default)
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
-static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
+static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp)
 {
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	if (!fp->jited) {
 		set_vm_flush_reset_perms(fp);
-		set_memory_ro((unsigned long)fp, fp->pages);
+		return set_memory_ro((unsigned long)fp, fp->pages);
 	}
 #endif
+	return 0;
 }
 
-static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
+static inline int __must_check
+bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
 	set_vm_flush_reset_perms(hdr);
-	set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT);
+	return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT);
 }
 
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);

include/linux/trace_events.h

@@ -765,8 +765,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
 int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie);
 void perf_event_detach_bpf_prog(struct perf_event *event);
 int perf_event_query_prog_array(struct perf_event *event, void __user *info);
-int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
-int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+
+struct bpf_raw_tp_link;
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link);
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link);
+
 struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name);
 void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp);
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
@@ -794,11 +797,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info)
 {
 	return -EOPNOTSUPP;
 }
-static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+struct bpf_raw_tp_link;
+static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link)
 {
 	return -EOPNOTSUPP;
 }
-static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link)
 {
 	return -EOPNOTSUPP;
 }
@@ -909,31 +913,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp);
 int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie);
 void perf_event_free_bpf_prog(struct perf_event *event);
 
-void bpf_trace_run1(struct bpf_prog *prog, u64 arg1);
-void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2);
-void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1);
+void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2);
+void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3);
-void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4);
-void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5);
-void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6);
-void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7);
-void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		    u64 arg8);
-void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		    u64 arg8, u64 arg9);
-void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		     u64 arg8, u64 arg9, u64 arg10);
-void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		     u64 arg8, u64 arg9, u64 arg10, u64 arg11);
-void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		     u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12);
 void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,

include/trace/bpf_probe.h

@@ -46,8 +46,7 @@
 static notrace void							\
 __bpf_trace_##call(void *__data, proto)					\
 {									\
-	struct bpf_prog *prog = __data;					\
-	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args));	\
+	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args));	\
 }
 
 #undef DECLARE_EVENT_CLASS

include/uapi/linux/bpf.h

@@ -1662,8 +1662,10 @@ union bpf_attr {
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
-		__u64 name;
-		__u32 prog_fd;
+		__u64		name;
+		__u32		prog_fd;
+		__u32		:32;
+		__aligned_u64	cookie;
 	} raw_tracepoint;
 
 	struct { /* anonymous struct for BPF_BTF_LOAD */

kernel/bpf/bpf_struct_ops.c

@@ -728,8 +728,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			cur_image = image;
 			trampoline_start = 0;
 		}
-		if (err < 0)
-			goto reset_unlock;
 
 		*(void **)(kdata + moff) = image + trampoline_start + cfi_get_offset();
 
@@ -742,8 +740,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		if (err)
 			goto reset_unlock;
 	}
-	for (i = 0; i < st_map->image_pages_cnt; i++)
-		arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE);
+	for (i = 0; i < st_map->image_pages_cnt; i++) {
+		err = arch_protect_bpf_trampoline(st_map->image_pages[i],
+						  PAGE_SIZE);
+		if (err)
+			goto reset_unlock;
+	}
 
 	if (st_map->map.map_flags & BPF_F_LINK) {
 		err = 0;

kernel/bpf/cgroup.c

@@ -2575,8 +2575,6 @@ cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	switch (func_id) {
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
-	case BPF_FUNC_get_current_pid_tgid:
-		return &bpf_get_current_pid_tgid_proto;
 	case BPF_FUNC_get_current_comm:
 		return &bpf_get_current_comm_proto;
 #ifdef CONFIG_CGROUP_NET_CLASSID

kernel/bpf/core.c

@@ -908,23 +908,30 @@ static LIST_HEAD(pack_list);
 static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns)
 {
 	struct bpf_prog_pack *pack;
+	int err;
 
 	pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)),
 		       GFP_KERNEL);
 	if (!pack)
 		return NULL;
 	pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE);
-	if (!pack->ptr) {
-		kfree(pack);
-		return NULL;
-	}
+	if (!pack->ptr)
+		goto out;
 	bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE);
 	bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE);
-	list_add_tail(&pack->list, &pack_list);
 
 	set_vm_flush_reset_perms(pack->ptr);
-	set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE);
+	err = set_memory_rox((unsigned long)pack->ptr,
+			     BPF_PROG_PACK_SIZE / PAGE_SIZE);
+	if (err)
+		goto out;
+	list_add_tail(&pack->list, &pack_list);
 	return pack;
+
+out:
+	bpf_jit_free_exec(pack->ptr);
+	kfree(pack);
+	return NULL;
 }
 
 void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
@@ -939,9 +946,16 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 		size = round_up(size, PAGE_SIZE);
 		ptr = bpf_jit_alloc_exec(size);
 		if (ptr) {
+			int err;
+
 			bpf_fill_ill_insns(ptr, size);
 			set_vm_flush_reset_perms(ptr);
-			set_memory_rox((unsigned long)ptr, size / PAGE_SIZE);
+			err = set_memory_rox((unsigned long)ptr,
+					     size / PAGE_SIZE);
+			if (err) {
+				bpf_jit_free_exec(ptr);
+				ptr = NULL;
+			}
 		}
 		goto out;
 	}
@@ -2403,7 +2417,9 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	}
 
 finalize:
-	bpf_prog_lock_ro(fp);
+	*err = bpf_prog_lock_ro(fp);
+	if (*err)
+		return fp;
 
 	/* The tail call compatibility check can only be done at
 	 * this late stage as we need to determine, if we deal

kernel/bpf/helpers.c

@@ -1730,6 +1730,10 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_strtol_proto;
 	case BPF_FUNC_strtoul:
 		return &bpf_strtoul_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_ns_current_pid_tgid:
+		return &bpf_get_ns_current_pid_tgid_proto;
 	default:
 		break;
 	}

kernel/bpf/lpm_trie.c

@@ -155,16 +155,17 @@ static inline int extract_bit(const u8 *data, size_t index)
 }
 
 /**
- * longest_prefix_match() - determine the longest prefix
+ * __longest_prefix_match() - determine the longest prefix
  * @trie:	The trie to get internal sizes from
  * @node:	The node to operate on
  * @key:	The key to compare to @node
  *
  * Determine the longest prefix of @node that matches the bits in @key.
  */
-static size_t longest_prefix_match(const struct lpm_trie *trie,
-				   const struct lpm_trie_node *node,
-				   const struct bpf_lpm_trie_key_u8 *key)
+static __always_inline
+size_t __longest_prefix_match(const struct lpm_trie *trie,
+			      const struct lpm_trie_node *node,
+			      const struct bpf_lpm_trie_key_u8 *key)
 {
 	u32 limit = min(node->prefixlen, key->prefixlen);
 	u32 prefixlen = 0, i = 0;
@@ -224,6 +225,13 @@ static size_t longest_prefix_match(const struct lpm_trie *trie,
 	return prefixlen;
 }
 
+static size_t longest_prefix_match(const struct lpm_trie *trie,
+				   const struct lpm_trie_node *node,
+				   const struct bpf_lpm_trie_key_u8 *key)
+{
+	return __longest_prefix_match(trie, node, key);
+}
+
 /* Called from syscall or from eBPF program */
 static void *trie_lookup_elem(struct bpf_map *map, void *_key)
 {
@@ -245,7 +253,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
 		 * If it's the maximum possible prefix for this trie, we have
 		 * an exact match and can return it directly.
 		 */
-		matchlen = longest_prefix_match(trie, node, key);
+		matchlen = __longest_prefix_match(trie, node, key);
 		if (matchlen == trie->max_prefixlen) {
 			found = node;
 			break;

kernel/bpf/syscall.c

@@ -3469,17 +3469,12 @@ out_put_prog:
 	return err;
 }
 
-struct bpf_raw_tp_link {
-	struct bpf_link link;
-	struct bpf_raw_event_map *btp;
-};
-
 static void bpf_raw_tp_link_release(struct bpf_link *link)
 {
 	struct bpf_raw_tp_link *raw_tp =
 		container_of(link, struct bpf_raw_tp_link, link);
 
-	bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog);
+	bpf_probe_unregister(raw_tp->btp, raw_tp);
 	bpf_put_raw_tracepoint(raw_tp->btp);
 }
 
@@ -3779,7 +3774,7 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro
 #endif /* CONFIG_PERF_EVENTS */
 
 static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
-				  const char __user *user_tp_name)
+				  const char __user *user_tp_name, u64 cookie)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_raw_tp_link *link;
@@ -3826,6 +3821,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 	bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
 		      &bpf_raw_tp_link_lops, prog);
 	link->btp = btp;
+	link->cookie = cookie;
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err) {
@@ -3833,7 +3829,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 		goto out_put_btp;
 	}
 
-	err = bpf_probe_register(link->btp, prog);
+	err = bpf_probe_register(link->btp, link);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		goto out_put_btp;
@@ -3846,11 +3842,13 @@ out_put_btp:
 	return err;
 }
 
-#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
+#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie
 
 static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 {
 	struct bpf_prog *prog;
+	void __user *tp_name;
+	__u64 cookie;
 	int fd;
 
 	if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN))
@@ -3860,7 +3858,9 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	fd = bpf_raw_tp_link_attach(prog, u64_to_user_ptr(attr->raw_tracepoint.name));
+	tp_name = u64_to_user_ptr(attr->raw_tracepoint.name);
+	cookie = attr->raw_tracepoint.cookie;
+	fd = bpf_raw_tp_link_attach(prog, tp_name, cookie);
 	if (fd < 0)
 		bpf_prog_put(prog);
 	return fd;
@@ -5198,7 +5198,7 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 			goto out;
 		}
 		if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
-			ret = bpf_raw_tp_link_attach(prog, NULL);
+			ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie);
 		else if (prog->expected_attach_type == BPF_TRACE_ITER)
 			ret = bpf_iter_link_attach(attr, uattr, prog);
 		else if (prog->expected_attach_type == BPF_LSM_CGROUP)