This adds a helper for bpf programs to access the memory of other
tasks. This also adds the ability for bpf iterator programs to
be sleepable.
This changes `bpf_iter_run_prog` to use the appropriate synchronization for
sleepable bpf programs. With sleepable bpf iterator programs, we can no
longer use `rcu_read_lock()` and must use `rcu_read_lock_trace()` instead
to protect the bpf program.
As an example use case at Meta, we are using a bpf task iterator program
and this new helper to print C++ async stack traces for all threads of
a given process.
Signed-off-by: Kenny Yu <kennyyu@xxxxxx>
---
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 11 +++++++++++
kernel/bpf/bpf_iter.c | 20 +++++++++++++++-----
kernel/bpf/helpers.c | 21 +++++++++++++++++++++
kernel/trace/bpf_trace.c | 2 ++
tools/include/uapi/linux/bpf.h | 11 +++++++++++
6 files changed, 61 insertions(+), 5 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6e947cd91152..d3d0ef8df148 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2222,6 +2222,7 @@ extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
extern const struct bpf_func_proto bpf_find_vma_proto;
extern const struct bpf_func_proto bpf_loop_proto;
extern const struct bpf_func_proto bpf_strncmp_proto;
+extern const struct bpf_func_proto bpf_access_process_vm_proto;
const struct bpf_func_proto *tracing_prog_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b0383d371b9a..27c2a18d5941 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5018,6 +5018,16 @@ union bpf_attr {
*
* Return
* The number of arguments of the traced function.
+ *
+ * long bpf_access_process_vm(void *dst, u32 size, const void *unsafe_ptr, struct task_struct *tsk, u32 flags)
+ * Description
+ * Read *size* bytes from user space address *unsafe_ptr* in *tsk*'s
+ * address space, and stores the data in *dst*. *flags* is not
+ * used yet and is provided for future extensibility. This is a
+ * wrapper of **access_process_vm**\ ().
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5206,6 +5216,7 @@ union bpf_attr {
FN(get_func_arg), \
FN(get_func_ret), \
FN(get_func_arg_cnt), \
+ FN(access_process_vm), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index b7aef5b3416d..110029ede71e 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -5,6 +5,7 @@
#include <linux/anon_inodes.h>
#include <linux/filter.h>
#include <linux/bpf.h>
+#include <linux/rcupdate_trace.h>
struct bpf_iter_target_info {
struct list_head list;
@@ -684,11 +685,20 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
{
int ret;
- rcu_read_lock();
- migrate_disable();
- ret = bpf_prog_run(prog, ctx);
- migrate_enable();
- rcu_read_unlock();
+ if (prog->aux->sleepable) {
+ rcu_read_lock_trace();
+ migrate_disable();
+ might_fault();
+ ret = bpf_prog_run(prog, ctx);
+ migrate_enable();
+ rcu_read_unlock_trace();
+ } else {
+ rcu_read_lock();
+ migrate_disable();
+ ret = bpf_prog_run(prog, ctx);
+ migrate_enable();
+ rcu_read_unlock();
+ }
/* bpf program can only return 0 or 1:
* 0 : okay
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 01cfdf40c838..30f1067ca8dc 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -16,6 +16,7 @@
#include <linux/pid_namespace.h>
#include <linux/proc_ns.h>
#include <linux/security.h>
+#include <linux/btf_ids.h>
#include "../../lib/kstrtox.h"
@@ -671,6 +672,26 @@ const struct bpf_func_proto bpf_copy_from_user_proto = {
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_5(bpf_access_process_vm, void *, dst, u32, size,
+ const void __user *, user_ptr, struct task_struct *, tsk,
+ u32, flags)
+{
+ /* flags is not used yet */
+ return access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0);
+}
+
+const struct bpf_func_proto bpf_access_process_vm_proto = {
+ .func = bpf_access_process_vm,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_BTF_ID,
+ .arg4_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
+ .arg5_type = ARG_ANYTHING
+};
+
BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
{
if (cpu >= nr_cpu_ids)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 21aa30644219..1a6a81ce2e36 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1257,6 +1257,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_find_vma_proto;
case BPF_FUNC_trace_vprintk:
return bpf_get_trace_vprintk_proto();
+ case BPF_FUNC_access_process_vm:
+ return prog->aux->sleepable ? &bpf_access_process_vm_proto : NULL;
default:
return bpf_base_func_proto(func_id);
}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b0383d371b9a..27c2a18d5941 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5018,6 +5018,16 @@ union bpf_attr {
*
* Return
* The number of arguments of the traced function.
+ *
+ * long bpf_access_process_vm(void *dst, u32 size, const void *unsafe_ptr, struct task_struct *tsk, u32 flags)
+ * Description
+ * Read *size* bytes from user space address *unsafe_ptr* in *tsk*'s
+ * address space, and stores the data in *dst*. *flags* is not
+ * used yet and is provided for future extensibility. This is a
+ * wrapper of **access_process_vm**\ ().
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5206,6 +5216,7 @@ union bpf_attr {
FN(get_func_arg), \
FN(get_func_ret), \
FN(get_func_arg_cnt), \
+ FN(access_process_vm), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
--
2.30.2
