If there is a large number (hundreds) of dmabufs allocated, the text output generated from dmabuf_iter_seq_show can exceed common user buffer sizes (e.g. PAGE_SIZE) necessitating multiple start/stop cycles to iterate through all dmabufs. However the dmabuf iterator currently returns NULL in dmabuf_iter_seq_start for all non-zero pos values, which results in the truncation of the output before all dmabufs are handled.
After dma_buf_iter_begin / dma_buf_iter_next, the refcount of the buffer is elevated so that the BPF iterator program can run without holding any locks. When a stop occurs, instead of immediately dropping the reference on the buffer, stash a pointer to the buffer in seq->priv until either start is called or the iterator is released. This also enables the resumption of iteration without first walking through the list of dmabufs based on the pos value.
Fixes: 76ea95534995 ("bpf: Add dmabuf iterator") Signed-off-by: T.J. Mercier tjmercier@google.com --- kernel/bpf/dmabuf_iter.c | 56 +++++++++++++++++++++++++++++++++++----- 1 file changed, 49 insertions(+), 7 deletions(-)
diff --git a/kernel/bpf/dmabuf_iter.c b/kernel/bpf/dmabuf_iter.c index 4dd7ef7c145c..cd500248abd9 100644 --- a/kernel/bpf/dmabuf_iter.c +++ b/kernel/bpf/dmabuf_iter.c @@ -6,10 +6,33 @@ #include <linux/kernel.h> #include <linux/seq_file.h>
+struct dmabuf_iter_priv { + /* + * If this pointer is non-NULL, the buffer's refcount is elevated to + * prevent destruction between stop/start. If reading is not resumed and + * start is never called again, then dmabuf_iter_seq_fini drops the + * reference when the iterator is released. + */ + struct dma_buf *dmabuf; +}; + static void *dmabuf_iter_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos) - return NULL; + struct dmabuf_iter_priv *p = seq->private; + + if (*pos) { + struct dma_buf *dmabuf = p->dmabuf; + + if (!dmabuf) + return NULL; + + /* + * Always resume from where we stopped, regardless of the value + * of pos. + */ + p->dmabuf = NULL; + return dmabuf; + }
return dma_buf_iter_begin(); } @@ -54,8 +77,11 @@ static void dmabuf_iter_seq_stop(struct seq_file *seq, void *v) { struct dma_buf *dmabuf = v;
- if (dmabuf) - dma_buf_put(dmabuf); + if (dmabuf) { + struct dmabuf_iter_priv *p = seq->private; + + p->dmabuf = dmabuf; + } }
static const struct seq_operations dmabuf_iter_seq_ops = { @@ -71,11 +97,27 @@ static void bpf_iter_dmabuf_show_fdinfo(const struct bpf_iter_aux_info *aux, seq_puts(seq, "dmabuf iter\n"); }
+static int dmabuf_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux) +{ + struct dmabuf_iter_priv *p = (struct dmabuf_iter_priv *)priv; + + p->dmabuf = NULL; + return 0; +} + +static void dmabuf_iter_seq_fini(void *priv) +{ + struct dmabuf_iter_priv *p = (struct dmabuf_iter_priv *)priv; + + if (p->dmabuf) + dma_buf_put(p->dmabuf); +} + static const struct bpf_iter_seq_info dmabuf_iter_seq_info = { .seq_ops = &dmabuf_iter_seq_ops, - .init_seq_private = NULL, - .fini_seq_private = NULL, - .seq_priv_size = 0, + .init_seq_private = dmabuf_iter_seq_init, + .fini_seq_private = dmabuf_iter_seq_fini, + .seq_priv_size = sizeof(struct dmabuf_iter_priv), };
static struct bpf_iter_reg bpf_dmabuf_reg_info = {
base-commit: 30f09200cc4aefbd8385b01e41bde2e4565a6f0e