On Mon, Aug 21, 2023 at 10:34 AM Dave Marchevsky <davemarchevsky@xxxxxx> wrote:
>
> This patch adds kfuncs bpf_iter_task_vma_{new,next,destroy} which allow
> creation and manipulation of struct bpf_iter_task_vma in open-coded
> iterator style. BPF programs can use these kfuncs directly or through
> bpf_for_each macro for natural-looking iteration of all task vmas.
>
> The implementation borrows heavily from bpf_find_vma helper's locking -
> differing only in that it holds the mmap_read lock for all iterations
> while the helper only executes its provided callback on a maximum of 1
> vma. Aside from locking, struct vma_iterator and vma_next do all the
> heavy lifting.
>
> The newly-added struct bpf_iter_task_vma has a name collision with a
> selftest for the seq_file task_vma iter's bpf skel, so the selftests/bpf/progs
> file is renamed in order to avoid the collision.
>
> Signed-off-by: Dave Marchevsky <davemarchevsky@xxxxxx>
> Cc: Nathan Slingerland <slinger@xxxxxxxx>
> ---
> include/uapi/linux/bpf.h | 4 +
> kernel/bpf/helpers.c | 3 +
> kernel/bpf/task_iter.c | 79 +++++++++++++++++++
> tools/include/uapi/linux/bpf.h | 5 ++
> tools/lib/bpf/bpf_helpers.h | 8 ++
> .../selftests/bpf/prog_tests/bpf_iter.c | 26 +++---
> ...f_iter_task_vma.c => bpf_iter_task_vmas.c} | 0
> 7 files changed, 112 insertions(+), 13 deletions(-)
> rename tools/testing/selftests/bpf/progs/{bpf_iter_task_vma.c => bpf_iter_task_vmas.c} (100%)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index d21deb46f49f..d90f9bf8080f 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -7291,4 +7291,8 @@ struct bpf_iter_num {
> __u64 __opaque[1];
> } __attribute__((aligned(8)));
>
> +struct bpf_iter_task_vma {
> + __u64 __opaque[4]; /* See bpf_iter_num comment above */
> +} __attribute__((aligned(8)));
> +
> #endif /* _UAPI__LINUX_BPF_H__ */
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index eb91cae0612a..7a06dea749f1 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2482,6 +2482,9 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
> BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW)
> BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL)
> BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
> +BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW)
> +BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
> +BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
> BTF_ID_FLAGS(func, bpf_dynptr_adjust)
> BTF_ID_FLAGS(func, bpf_dynptr_is_null)
> BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
> diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
> index c4ab9d6cdbe9..fb934ca9e020 100644
> --- a/kernel/bpf/task_iter.c
> +++ b/kernel/bpf/task_iter.c
> @@ -7,7 +7,9 @@
> #include <linux/fs.h>
> #include <linux/fdtable.h>
> #include <linux/filter.h>
> +#include <linux/bpf_mem_alloc.h>
> #include <linux/btf_ids.h>
> +#include <linux/mm_types.h>
> #include "mmap_unlock_work.h"
>
> static const char * const iter_task_type_names[] = {
> @@ -823,6 +825,83 @@ const struct bpf_func_proto bpf_find_vma_proto = {
> .arg5_type = ARG_ANYTHING,
> };
>
> +/* Non-opaque version of uapi bpf_iter_task_vma */
> +struct bpf_iter_task_vma_kern {
> + struct task_struct *task;
> + struct mm_struct *mm;
> + struct mmap_unlock_irq_work *work;
> + struct vma_iterator *vmi;
> +} __attribute__((aligned(8)));
> +
> +__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
> + struct task_struct *task, u64 addr)
> +{
> + struct bpf_iter_task_vma_kern *kit = (void *)it;
> + bool irq_work_busy = false;
> + int err;
> +
> + BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma));
> + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma));
> +
> + /* NULL i->mm signals failed bpf_iter_task_vma initialization.
> + * i->work == NULL is valid.
> + */
> + kit->mm = NULL;
> + kit->task = NULL;
> + if (!task)
> + return -ENOENT;
> +
> + kit->task = get_task_struct(task);
> + kit->mm = task->mm;
> + if (!kit->mm) {
> + err = -ENOENT;
> + goto err_put_task;
> + }
> +
> + kit->vmi = bpf_mem_alloc(&bpf_global_ma, sizeof(struct vma_iterator));
> + if (!kit->vmi) {
> + err = -ENOMEM;
> + goto err_put_task;
> + }
Since alloc is done anyway, let's alloc the whole bpf_iter_task_vma_kern
and reduce bpf prog side to a single pointer?
