diff mbox series

[v7,bpf-next,2/4] bpf: Add bpf_copy_from_user_task() helper

Message ID 20220124185403.468466-3-kennyyu@fb.com (mailing list archive)
State Accepted
Commit 376040e47334c6dc6a939a32197acceb00fe4acf
Delegated to: BPF
Headers show
Series Add bpf_copy_from_user_task helper and sleepable bpf iterator programs | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for bpf-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1807 this patch: 1807
netdev/cc_maintainers warning 8 maintainers not CCed: rostedt@goodmis.org joe@cilium.io kpsingh@kernel.org john.fastabend@gmail.com kafai@fb.com songliubraving@fb.com mingo@redhat.com netdev@vger.kernel.org
netdev/build_clang success Errors and warnings before: 222 this patch: 222
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1824 this patch: 1824
netdev/checkpatch warning WARNING: line length of 110 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next fail VM_Test
bpf/vmtest-bpf-next-PR fail PR summary

Commit Message

Kenny Yu Jan. 24, 2022, 6:54 p.m. UTC 
This adds a helper for bpf programs to read the memory of other
tasks.

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@fb.com>
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 11 +++++++++++
 kernel/bpf/helpers.c           | 34 ++++++++++++++++++++++++++++++++++
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h | 11 +++++++++++
 5 files changed, 59 insertions(+)

Comments

Andrii Nakryiko Jan. 24, 2022, 10:18 p.m. UTC | #1 
On Mon, Jan 24, 2022 at 10:54 AM Kenny Yu <kennyyu@fb.com> wrote:
>
> This adds a helper for bpf programs to read the memory of other
> tasks.
>
> 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@fb.com>
> ---

LGTM.

Acked-by: Andrii Nakryiko <andrii@kernel.org>

>  include/linux/bpf.h            |  1 +
>  include/uapi/linux/bpf.h       | 11 +++++++++++
>  kernel/bpf/helpers.c           | 34 ++++++++++++++++++++++++++++++++++
>  kernel/trace/bpf_trace.c       |  2 ++
>  tools/include/uapi/linux/bpf.h | 11 +++++++++++
>  5 files changed, 59 insertions(+)
>

[...]

> +       ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0);
> +       if (ret == size)
> +               return 0;
> +
> +       memset(dst, 0, size);
> +       /* Return -EFAULT for partial read */
> +       return (ret < 0) ? ret : -EFAULT;

nit: unnecessary ()

> +}
> +
> +const struct bpf_func_proto bpf_copy_from_user_task_proto = {
> +       .func           = bpf_copy_from_user_task,
> +       .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
> +};
> +

[...]
Alexei Starovoitov Jan. 25, 2022, 4:06 a.m. UTC | #2 
On Mon, Jan 24, 2022 at 2:18 PM Andrii Nakryiko
<andrii.nakryiko@gmail.com> wrote:
>
> On Mon, Jan 24, 2022 at 10:54 AM Kenny Yu <kennyyu@fb.com> wrote:
> >
> > This adds a helper for bpf programs to read the memory of other
> > tasks.
> >
> > 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@fb.com>
> > ---
>
> LGTM.
>
> Acked-by: Andrii Nakryiko <andrii@kernel.org>
>
> >  include/linux/bpf.h            |  1 +
> >  include/uapi/linux/bpf.h       | 11 +++++++++++
> >  kernel/bpf/helpers.c           | 34 ++++++++++++++++++++++++++++++++++
> >  kernel/trace/bpf_trace.c       |  2 ++
> >  tools/include/uapi/linux/bpf.h | 11 +++++++++++
> >  5 files changed, 59 insertions(+)
> >
>
> [...]
>
> > +       ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0);
> > +       if (ret == size)
> > +               return 0;
> > +
> > +       memset(dst, 0, size);
> > +       /* Return -EFAULT for partial read */
> > +       return (ret < 0) ? ret : -EFAULT;
>
> nit: unnecessary ()

I fixed it while applying.
Also added a few unlikely().

Thanks everyone!
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e8ec8d2f2fe3..4f13642c6a47 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2238,6 +2238,7 @@  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_copy_from_user_task_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 16a7574292a5..4a2f7041ebae 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5076,6 +5076,16 @@  union bpf_attr {
  *		associated to *xdp_md*, at *offset*.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ *	Description
+ *		Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ *		address space, and stores the data in *dst*. *flags* is not
+ *		used yet and is provided for future extensibility. This helper
+ *		can only be used by sleepable programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure. On error
+ *		*dst* buffer is zeroed out.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5269,6 +5279,7 @@  union bpf_attr {
 	FN(xdp_get_buff_len),		\
 	FN(xdp_load_bytes),		\
 	FN(xdp_store_bytes),		\
+	FN(copy_from_user_task),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 01cfdf40c838..2688b0064289 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 +672,39 @@  const struct bpf_func_proto bpf_copy_from_user_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size,
+	   const void __user *, user_ptr, struct task_struct *, tsk, u64, flags)
+{
+	int ret;
+
+	/* flags is not used yet */
+	if (flags)
+		return -EINVAL;
+
+	if (size == 0)
+		return 0;
+
+	ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0);
+	if (ret == size)
+		return 0;
+
+	memset(dst, 0, size);
+	/* Return -EFAULT for partial read */
+	return (ret < 0) ? ret : -EFAULT;
+}
+
+const struct bpf_func_proto bpf_copy_from_user_task_proto = {
+	.func		= bpf_copy_from_user_task,
+	.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 06a9e220069e..a2024ba32a20 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1235,6 +1235,8 @@  bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+	case BPF_FUNC_copy_from_user_task:
+		return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_per_cpu_ptr:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 16a7574292a5..4a2f7041ebae 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5076,6 +5076,16 @@  union bpf_attr {
  *		associated to *xdp_md*, at *offset*.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ *	Description
+ *		Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ *		address space, and stores the data in *dst*. *flags* is not
+ *		used yet and is provided for future extensibility. This helper
+ *		can only be used by sleepable programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure. On error
+ *		*dst* buffer is zeroed out.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5269,6 +5279,7 @@  union bpf_attr {
 	FN(xdp_get_buff_len),		\
 	FN(xdp_load_bytes),		\
 	FN(xdp_store_bytes),		\
+	FN(copy_from_user_task),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper