Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
bpf 2021-08-10

We've added 5 non-merge commits during the last 2 day(s) which contain
a total of 7 files changed, 27 insertions(+), 15 deletions(-).

1) Fix missing bpf_read_lock_trace() context for BPF loader progs, from Yonghong Song.

2) Fix corner case where BPF prog retrieves wrong local storage, also from Yonghong Song.

3) Restrict availability of BPF write_user helper behind lockdown, from Daniel Borkmann.

4) Fix multiple kernel-doc warnings in BPF core, from Randy Dunlap.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, core: Fix kernel-doc notation
  bpf: Fix potentially incorrect results with bpf_get_local_storage()
  bpf: Add missing bpf_read_[un]lock_trace() for syscall program
  bpf: Add lockdown check for probe_write_user helper
  bpf: Add _kernel suffix to internal lockdown_bpf_read
====================

Link: https://lore.kernel.org/r/20210810144025.22814-1-daniel@iogearbox.netSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/bpf-cgroup.h

@@ -201,8 +201,8 @@ static inline void bpf_cgroup_storage_unset(void)
 {
 	int i;
 
-	for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) {
-		if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current))
+	for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) {
+		if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current))
 			continue;
 
 		this_cpu_write(bpf_cgroup_storage_info[i].task, NULL);

include/linux/security.h

@@ -120,10 +120,11 @@ enum lockdown_reason {
 	LOCKDOWN_MMIOTRACE,
 	LOCKDOWN_DEBUGFS,
 	LOCKDOWN_XMON_WR,
+	LOCKDOWN_BPF_WRITE_USER,
 	LOCKDOWN_INTEGRITY_MAX,
 	LOCKDOWN_KCORE,
 	LOCKDOWN_KPROBES,
-	LOCKDOWN_BPF_READ,
+	LOCKDOWN_BPF_READ_KERNEL,
 	LOCKDOWN_PERF,
 	LOCKDOWN_TRACEFS,
 	LOCKDOWN_XMON_RW,

kernel/bpf/core.c

@@ -1362,11 +1362,13 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
 }
 
 /**
- *	__bpf_prog_run - run eBPF program on a given context
+ *	___bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
  *	@insn: is the array of eBPF instructions
  *
  * Decode and execute eBPF instructions.
+ *
+ * Return: whatever value is in %BPF_R0 at program exit
  */
 static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
 {
@@ -1878,6 +1880,9 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
  *
  * Try to JIT eBPF program, if JIT is not available, use interpreter.
  * The BPF program will be executed via BPF_PROG_RUN() macro.
+ *
+ * Return: the &fp argument along with &err set to 0 for success or
+ * a negative errno code on failure
  */
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 {

kernel/bpf/helpers.c

@@ -397,8 +397,8 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
 	void *ptr;
 	int i;
 
-	for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) {
-		if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current))
+	for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) {
+		if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current))
 			continue;
 
 		storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]);
@@ -1070,12 +1070,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_probe_read_user:
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
-		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_kernel_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
-		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_kernel_str_proto;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;

kernel/trace/bpf_trace.c

@@ -990,28 +990,29 @@ 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_probe_write_user:
-		return bpf_get_probe_write_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:
+		return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ?
+		       NULL : bpf_get_probe_write_proto();
 	case BPF_FUNC_probe_read_user:
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
-		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_kernel_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
-		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_kernel_str_proto;
 #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	case BPF_FUNC_probe_read:
-		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_str:
-		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_compat_str_proto;
 #endif
 #ifdef CONFIG_CGROUPS

net/bpf/test_run.c

@@ -7,6 +7,7 @@
 #include <linux/vmalloc.h>
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
+#include <linux/rcupdate_trace.h>
 #include <linux/sched/signal.h>
 #include <net/bpf_sk_storage.h>
 #include <net/sock.h>
@@ -951,7 +952,10 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog,
 			goto out;
 		}
 	}
+
+	rcu_read_lock_trace();
 	retval = bpf_prog_run_pin_on_cpu(prog, ctx);
+	rcu_read_unlock_trace();
 
 	if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) {
 		err = -EFAULT;

security/security.c

@@ -58,10 +58,11 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = {
 	[LOCKDOWN_MMIOTRACE] = "unsafe mmio",
 	[LOCKDOWN_DEBUGFS] = "debugfs access",
 	[LOCKDOWN_XMON_WR] = "xmon write access",
+	[LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM",
 	[LOCKDOWN_INTEGRITY_MAX] = "integrity",
 	[LOCKDOWN_KCORE] = "/proc/kcore access",
 	[LOCKDOWN_KPROBES] = "use of kprobes",
-	[LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM",
+	[LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM",
 	[LOCKDOWN_PERF] = "unsafe use of perf",
 	[LOCKDOWN_TRACEFS] = "use of tracefs",
 	[LOCKDOWN_XMON_RW] = "xmon read and write access",