Merge tag 'bpf-next-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Introduce '__attribute__((bpf_fastcall))' for helpers and kfuncs with
   corresponding support in LLVM.

   It is similar to existing 'no_caller_saved_registers' attribute in
   GCC/LLVM with a provision for backward compatibility. It allows
   compilers generate more efficient BPF code assuming the verifier or
   JITs will inline or partially inline a helper/kfunc with such
   attribute. bpf_cast_to_kern_ctx, bpf_rdonly_cast,
   bpf_get_smp_processor_id are the first set of such helpers.

 - Harden and extend ELF build ID parsing logic.

   When called from sleepable context the relevants parts of ELF file
   will be read to find and fetch .note.gnu.build-id information. Also
   harden the logic to avoid TOCTOU, overflow, out-of-bounds problems.

 - Improvements and fixes for sched-ext:
    - Allow passing BPF iterators as kfunc arguments
    - Make the pointer returned from iter_next method trusted
    - Fix x86 JIT convergence issue due to growing/shrinking conditional
      jumps in variable length encoding

 - BPF_LSM related:
    - Introduce few VFS kfuncs and consolidate them in
      fs/bpf_fs_kfuncs.c
    - Enforce correct range of return values from certain LSM hooks
    - Disallow attaching to other LSM hooks

 - Prerequisite work for upcoming Qdisc in BPF:
    - Allow kptrs in program provided structs
    - Support for gen_epilogue in verifier_ops

 - Important fixes:
    - Fix uprobe multi pid filter check
    - Fix bpf_strtol and bpf_strtoul helpers
    - Track equal scalars history on per-instruction level
    - Fix tailcall hierarchy on x86 and arm64
    - Fix signed division overflow to prevent INT_MIN/-1 trap on x86
    - Fix get kernel stack in BPF progs attached to tracepoint:syscall

 - Selftests:
    - Add uprobe bench/stress tool
    - Generate file dependencies to drastically improve re-build time
    - Match JIT-ed and BPF asm with __xlated/__jited keywords
    - Convert older tests to test_progs framework
    - Add support for RISC-V
    - Few fixes when BPF programs are compiled with GCC-BPF backend
      (support for GCC-BPF in BPF CI is ongoing in parallel)
    - Add traffic monitor
    - Enable cross compile and musl libc

* tag 'bpf-next-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (260 commits)
  btf: require pahole 1.21+ for DEBUG_INFO_BTF with default DWARF version
  btf: move pahole check in scripts/link-vmlinux.sh to lib/Kconfig.debug
  btf: remove redundant CONFIG_BPF test in scripts/link-vmlinux.sh
  bpf: Call the missed kfree() when there is no special field in btf
  bpf: Call the missed btf_record_free() when map creation fails
  selftests/bpf: Add a test case to write mtu result into .rodata
  selftests/bpf: Add a test case to write strtol result into .rodata
  selftests/bpf: Rename ARG_PTR_TO_LONG test description
  selftests/bpf: Fix ARG_PTR_TO_LONG {half-,}uninitialized test
  bpf: Zero former ARG_PTR_TO_{LONG,INT} args in case of error
  bpf: Improve check_raw_mode_ok test for MEM_UNINIT-tagged types
  bpf: Fix helper writes to read-only maps
  bpf: Remove truncation test in bpf_strtol and bpf_strtoul helpers
  bpf: Fix bpf_strtol and bpf_strtoul helpers for 32bit
  selftests/bpf: Add tests for sdiv/smod overflow cases
  bpf: Fix a sdiv overflow issue
  libbpf: Add bpf_object__token_fd accessor
  docs/bpf: Add missing BPF program types to docs
  docs/bpf: Add constant values for linkages
  bpf: Use fake pt_regs when doing bpf syscall tracepoint tracing
  ...

2 files changed, 18 insertions, 102 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ac0a01cc8634..a582cd25ca87 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -24,7 +24,6 @@
 #include <linux/key.h>
 #include <linux/verification.h>
 #include <linux/namei.h>
-#include <linux/fileattr.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -798,29 +797,6 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = {
 	.ret_btf_id	= &bpf_task_pt_regs_ids[0],
 };
 
-BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
-{
-	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct cgroup *cgrp;
-
-	if (unlikely(idx >= array->map.max_entries))
-		return -E2BIG;
-
-	cgrp = READ_ONCE(array->ptrs[idx]);
-	if (unlikely(!cgrp))
-		return -EAGAIN;
-
-	return task_under_cgroup_hierarchy(current, cgrp);
-}
-
-static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
-	.func           = bpf_current_task_under_cgroup,
-	.gpl_only       = false,
-	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_CONST_MAP_PTR,
-	.arg2_type      = ARG_ANYTHING,
-};
-
 struct send_signal_irq_work {
 	struct irq_work irq_work;
 	struct task_struct *task;
@@ -1226,7 +1202,8 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_ANYTHING,
-	.arg3_type	= ARG_PTR_TO_LONG,
+	.arg3_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg3_size	= sizeof(u64),
 };
 
 BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
@@ -1242,7 +1219,8 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = {
 	.func		= get_func_ret,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_LONG,
+	.arg2_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg2_size	= sizeof(u64),
 };
 
 BPF_CALL_1(get_func_arg_cnt, void *, ctx)
@@ -1439,73 +1417,6 @@ static int __init bpf_key_sig_kfuncs_init(void)
 late_initcall(bpf_key_sig_kfuncs_init);
 #endif /* CONFIG_KEYS */
 
-/* filesystem kfuncs */
-__bpf_kfunc_start_defs();
-
-/**
- * bpf_get_file_xattr - get xattr of a file
- * @file: file to get xattr from
- * @name__str: name of the xattr
- * @value_p: output buffer of the xattr value
- *
- * Get xattr *name__str* of *file* and store the output in *value_ptr*.
- *
- * For security reasons, only *name__str* with prefix "user." is allowed.
- *
- * Return: 0 on success, a negative value on error.
- */
-__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
-				   struct bpf_dynptr *value_p)
-{
-	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
-	struct dentry *dentry;
-	u32 value_len;
-	void *value;
-	int ret;
-
-	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
-		return -EPERM;
-
-	value_len = __bpf_dynptr_size(value_ptr);
-	value = __bpf_dynptr_data_rw(value_ptr, value_len);
-	if (!value)
-		return -EINVAL;
-
-	dentry = file_dentry(file);
-	ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ);
-	if (ret)
-		return ret;
-	return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len);
-}
-
-__bpf_kfunc_end_defs();
-
-BTF_KFUNCS_START(fs_kfunc_set_ids)
-BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
-BTF_KFUNCS_END(fs_kfunc_set_ids)
-
-static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id)
-{
-	if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id))
-		return 0;
-
-	/* Only allow to attach from LSM hooks, to avoid recursion */
-	return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0;
-}
-
-static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
-	.owner = THIS_MODULE,
-	.set = &fs_kfunc_set_ids,
-	.filter = bpf_get_file_xattr_filter,
-};
-
-static int __init bpf_fs_kfuncs_init(void)
-{
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
-}
-
-late_initcall(bpf_fs_kfuncs_init);
-
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1548,8 +1459,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_numa_node_id_proto;
 	case BPF_FUNC_perf_event_read:
 		return &bpf_perf_event_read_proto;
-	case BPF_FUNC_current_task_under_cgroup:
-		return &bpf_current_task_under_cgroup_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_probe_write_user:
@@ -1578,6 +1487,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_cgrp_storage_get_proto;
 	case BPF_FUNC_cgrp_storage_delete:
 		return &bpf_cgrp_storage_delete_proto;
+	case BPF_FUNC_current_task_under_cgroup:
+		return &bpf_current_task_under_cgroup_proto;
 #endif
 	case BPF_FUNC_send_signal:
 		return &bpf_send_signal_proto;
@@ -1598,7 +1509,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_get_task_stack:
-		return &bpf_get_task_stack_proto;
+		return prog->sleepable ? &bpf_get_task_stack_sleepable_proto
+				       : &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return &bpf_copy_from_user_proto;
 	case BPF_FUNC_copy_from_user_task:
@@ -1654,7 +1566,7 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto;
+		return prog->sleepable ? &bpf_get_stack_sleepable_proto : &bpf_get_stack_proto;
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 	case BPF_FUNC_override_return:
 		return &bpf_override_return_proto;
@@ -3299,7 +3211,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 	struct bpf_run_ctx *old_run_ctx;
 	int err = 0;
 
-	if (link->task && current->mm != link->task->mm)
+	if (link->task && !same_thread_group(current, link->task))
 		return 0;
 
 	if (sleepable)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 9c581d6da843..785733245ead 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -564,6 +564,7 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
 	BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
 
 	/* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
+	perf_fetch_caller_regs(regs);
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	for (i = 0; i < sys_data->nb_args; i++)
@@ -575,6 +576,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
+	struct pt_regs *fake_regs;
 	struct hlist_head *head;
 	unsigned long args[6];
 	bool valid_prog_array;
@@ -602,7 +604,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	rec = perf_trace_buf_alloc(size, NULL, &rctx);
+	rec = perf_trace_buf_alloc(size, &fake_regs, &rctx);
 	if (!rec)
 		return;
 
@@ -611,7 +613,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	if ((valid_prog_array &&
-	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
+	     !perf_call_bpf_enter(sys_data->enter_event, fake_regs, sys_data, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
@@ -666,6 +668,7 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
 	} __aligned(8) param;
 
 	/* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
+	perf_fetch_caller_regs(regs);
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	param.ret = rec->ret;
@@ -676,6 +679,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
+	struct pt_regs *fake_regs;
 	struct hlist_head *head;
 	bool valid_prog_array;
 	int syscall_nr;
@@ -701,7 +705,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	rec = perf_trace_buf_alloc(size, NULL, &rctx);
+	rec = perf_trace_buf_alloc(size, &fake_regs, &rctx);
 	if (!rec)
 		return;
 
@@ -709,7 +713,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->ret = syscall_get_return_value(current, regs);
 
 	if ((valid_prog_array &&
-	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
+	     !perf_call_bpf_exit(sys_data->exit_event, fake_regs, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;