On Tue, Nov 15, 2022 at 8:16 AM Toke Høiland-Jørgensen <toke@xxxxxxxxxx> wrote:
>
> Stanislav Fomichev <sdf@xxxxxxxxxx> writes:
>
> > Kfuncs have to be defined with KF_UNROLL for an attempted unroll.
> > For now, only XDP programs can have their kfuncs unrolled, but
> > we can extend this later on if more programs would like to use it.
> >
> > For XDP, we define a new kfunc set (xdp_metadata_kfunc_ids) which
> > implements all possible metatada kfuncs. Not all devices have to
> > implement them. If unrolling is not supported by the target device,
> > the default implementation is called instead. The default
> > implementation is unconditionally unrolled to 'return false/0/NULL'
> > for now.
> >
> > Upon loading, if BPF_F_XDP_HAS_METADATA is passed via prog_flags,
> > we treat prog_index as target device for kfunc unrolling.
> > net_device_ops gains new ndo_unroll_kfunc which does the actual
> > dirty work per device.
> >
> > The kfunc unrolling itself largely follows the existing map_gen_lookup
> > unrolling example, so there is nothing new here.
> >
> > Cc: John Fastabend <john.fastabend@xxxxxxxxx>
> > Cc: David Ahern <dsahern@xxxxxxxxx>
> > Cc: Martin KaFai Lau <martin.lau@xxxxxxxxx>
> > Cc: Jakub Kicinski <kuba@xxxxxxxxxx>
> > Cc: Willem de Bruijn <willemb@xxxxxxxxxx>
> > Cc: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
> > Cc: Anatoly Burakov <anatoly.burakov@xxxxxxxxx>
> > Cc: Alexander Lobakin <alexandr.lobakin@xxxxxxxxx>
> > Cc: Magnus Karlsson <magnus.karlsson@xxxxxxxxx>
> > Cc: Maryam Tahhan <mtahhan@xxxxxxxxxx>
> > Cc: xdp-hints@xxxxxxxxxxxxxxx
> > Cc: netdev@xxxxxxxxxxxxxxx
> > Signed-off-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
> > ---
> > Documentation/bpf/kfuncs.rst | 8 +++++
> > include/linux/bpf.h | 1 +
> > include/linux/btf.h | 1 +
> > include/linux/btf_ids.h | 4 +++
> > include/linux/netdevice.h | 5 +++
> > include/net/xdp.h | 24 +++++++++++++
> > include/uapi/linux/bpf.h | 5 +++
> > kernel/bpf/syscall.c | 28 ++++++++++++++-
> > kernel/bpf/verifier.c | 65 ++++++++++++++++++++++++++++++++++
> > net/core/dev.c | 7 ++++
> > net/core/xdp.c | 39 ++++++++++++++++++++
> > tools/include/uapi/linux/bpf.h | 5 +++
> > 12 files changed, 191 insertions(+), 1 deletion(-)
> >
> > diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
> > index 0f858156371d..1723de2720bb 100644
> > --- a/Documentation/bpf/kfuncs.rst
> > +++ b/Documentation/bpf/kfuncs.rst
> > @@ -169,6 +169,14 @@ rebooting or panicking. Due to this additional restrictions apply to these
> > calls. At the moment they only require CAP_SYS_BOOT capability, but more can be
> > added later.
> >
> > +2.4.8 KF_UNROLL flag
> > +-----------------------
> > +
> > +The KF_UNROLL flag is used for kfuncs that the verifier can attempt to unroll.
> > +Unrolling is currently implemented only for XDP programs' metadata kfuncs.
> > +The main motivation behind unrolling is to remove function call overhead
> > +and allow efficient inlined kfuncs to be generated.
> > +
> > 2.5 Registering the kfuncs
> > --------------------------
> >
> > diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> > index 798aec816970..bf8936522dd9 100644
> > --- a/include/linux/bpf.h
> > +++ b/include/linux/bpf.h
> > @@ -1240,6 +1240,7 @@ struct bpf_prog_aux {
> > struct work_struct work;
> > struct rcu_head rcu;
> > };
> > + const struct net_device_ops *xdp_kfunc_ndo;
> > };
> >
> > struct bpf_prog {
> > diff --git a/include/linux/btf.h b/include/linux/btf.h
> > index d80345fa566b..950cca997a5a 100644
> > --- a/include/linux/btf.h
> > +++ b/include/linux/btf.h
> > @@ -51,6 +51,7 @@
> > #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */
> > #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */
> > #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */
> > +#define KF_UNROLL (1 << 7) /* kfunc unrolling can be attempted */
> >
> > /*
> > * Return the name of the passed struct, if exists, or halt the build if for
> > diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
> > index c9744efd202f..eb448e9c79bb 100644
> > --- a/include/linux/btf_ids.h
> > +++ b/include/linux/btf_ids.h
> > @@ -195,6 +195,10 @@ asm( \
> > __BTF_ID_LIST(name, local) \
> > __BTF_SET8_START(name, local)
> >
> > +#define BTF_SET8_START_GLOBAL(name) \
> > +__BTF_ID_LIST(name, global) \
> > +__BTF_SET8_START(name, global)
> > +
> > #define BTF_SET8_END(name) \
> > asm( \
> > ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
> > diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> > index 02a2318da7c7..2096b4f00e4b 100644
> > --- a/include/linux/netdevice.h
> > +++ b/include/linux/netdevice.h
> > @@ -73,6 +73,8 @@ struct udp_tunnel_info;
> > struct udp_tunnel_nic_info;
> > struct udp_tunnel_nic;
> > struct bpf_prog;
> > +struct bpf_insn;
> > +struct bpf_patch;
> > struct xdp_buff;
> >
> > void synchronize_net(void);
> > @@ -1604,6 +1606,9 @@ struct net_device_ops {
> > ktime_t (*ndo_get_tstamp)(struct net_device *dev,
> > const struct skb_shared_hwtstamps *hwtstamps,
> > bool cycles);
> > + void (*ndo_unroll_kfunc)(const struct bpf_prog *prog,
> > + u32 func_id,
> > + struct bpf_patch *patch);
> > };
> >
> > /**
> > diff --git a/include/net/xdp.h b/include/net/xdp.h
> > index 55dbc68bfffc..2a82a98f2f9f 100644
> > --- a/include/net/xdp.h
> > +++ b/include/net/xdp.h
> > @@ -7,6 +7,7 @@
> > #define __LINUX_NET_XDP_H__
> >
> > #include <linux/skbuff.h> /* skb_shared_info */
> > +#include <linux/btf_ids.h> /* btf_id_set8 */
> >
> > /**
> > * DOC: XDP RX-queue information
> > @@ -409,4 +410,27 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
> >
> > #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE
> >
> > +#define XDP_METADATA_KFUNC_xxx \
> > + XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP_SUPPORTED, \
> > + bpf_xdp_metadata_rx_timestamp_supported) \
> > + XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \
> > + bpf_xdp_metadata_rx_timestamp) \
> > +
> > +enum {
> > +#define XDP_METADATA_KFUNC(name, str) name,
> > +XDP_METADATA_KFUNC_xxx
> > +#undef XDP_METADATA_KFUNC
> > +MAX_XDP_METADATA_KFUNC,
> > +};
> > +
> > +#ifdef CONFIG_DEBUG_INFO_BTF
> > +extern struct btf_id_set8 xdp_metadata_kfunc_ids;
> > +static inline u32 xdp_metadata_kfunc_id(int id)
> > +{
> > + return xdp_metadata_kfunc_ids.pairs[id].id;
> > +}
> > +#else
> > +static inline u32 xdp_metadata_kfunc_id(int id) { return 0; }
> > +#endif
> > +
> > #endif /* __LINUX_NET_XDP_H__ */
> > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> > index fb4c911d2a03..b444b1118c4f 100644
> > --- a/include/uapi/linux/bpf.h
> > +++ b/include/uapi/linux/bpf.h
> > @@ -1156,6 +1156,11 @@ enum bpf_link_type {
> > */
> > #define BPF_F_XDP_HAS_FRAGS (1U << 5)
> >
> > +/* If BPF_F_XDP_HAS_METADATA is used in BPF_PROG_LOAD command, the loaded
> > + * program becomes device-bound but can access it's XDP metadata.
> > + */
> > +#define BPF_F_XDP_HAS_METADATA (1U << 6)
> > +
> > /* link_create.kprobe_multi.flags used in LINK_CREATE command for
> > * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
> > */
> > diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> > index 85532d301124..597c41949910 100644
> > --- a/kernel/bpf/syscall.c
> > +++ b/kernel/bpf/syscall.c
> > @@ -2426,6 +2426,20 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
> > /* last field in 'union bpf_attr' used by this command */
> > #define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size
> >
> > +static int xdp_resolve_netdev(struct bpf_prog *prog, int ifindex)
> > +{
> > + struct net *net = current->nsproxy->net_ns;
> > + struct net_device *dev;
> > +
> > + for_each_netdev(net, dev) {
> > + if (dev->ifindex == ifindex) {
>
> So this is basically dev_get_by_index(), except you're not doing
> dev_hold()? Which also means there's no protection against the netdev
> going away?
Yeah, good point, will use dev_get_by_index here instead with proper refcnt..
> > + prog->aux->xdp_kfunc_ndo = dev->netdev_ops;
> > + return 0;
> > + }
> > + }
>
> > + return -EINVAL;
> > +}
> > +
> > static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
> > {
> > enum bpf_prog_type type = attr->prog_type;
> > @@ -2443,7 +2457,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
> > BPF_F_TEST_STATE_FREQ |
> > BPF_F_SLEEPABLE |
> > BPF_F_TEST_RND_HI32 |
> > - BPF_F_XDP_HAS_FRAGS))
> > + BPF_F_XDP_HAS_FRAGS |
> > + BPF_F_XDP_HAS_METADATA))
> > return -EINVAL;
> >
> > if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
> > @@ -2531,6 +2546,17 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
> > prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
> > prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
> >
> > + if (attr->prog_flags & BPF_F_XDP_HAS_METADATA) {
> > + /* Reuse prog_ifindex to carry request to unroll
> > + * metadata kfuncs.
> > + */
> > + prog->aux->offload_requested = false;
> > +
> > + err = xdp_resolve_netdev(prog, attr->prog_ifindex);
> > + if (err < 0)
> > + goto free_prog;
> > + }
> > +
> > err = security_bpf_prog_alloc(prog->aux);
> > if (err)
> > goto free_prog;
> > diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> > index 07c0259dfc1a..b657ed6eb277 100644
> > --- a/kernel/bpf/verifier.c
> > +++ b/kernel/bpf/verifier.c
> > @@ -9,6 +9,7 @@
> > #include <linux/types.h>
> > #include <linux/slab.h>
> > #include <linux/bpf.h>
> > +#include <linux/bpf_patch.h>
> > #include <linux/btf.h>
> > #include <linux/bpf_verifier.h>
> > #include <linux/filter.h>
> > @@ -14015,6 +14016,43 @@ static int fixup_call_args(struct bpf_verifier_env *env)
> > return err;
> > }
> >
> > +static int unroll_kfunc_call(struct bpf_verifier_env *env,
> > + struct bpf_insn *insn,
> > + struct bpf_patch *patch)
> > +{
> > + enum bpf_prog_type prog_type;
> > + struct bpf_prog_aux *aux;
> > + struct btf *desc_btf;
> > + u32 *kfunc_flags;
> > + u32 func_id;
> > +
> > + desc_btf = find_kfunc_desc_btf(env, insn->off);
> > + if (IS_ERR(desc_btf))
> > + return PTR_ERR(desc_btf);
> > +
> > + prog_type = resolve_prog_type(env->prog);
> > + func_id = insn->imm;
> > +
> > + kfunc_flags = btf_kfunc_id_set_contains(desc_btf, prog_type, func_id);
> > + if (!kfunc_flags)
> > + return 0;
> > + if (!(*kfunc_flags & KF_UNROLL))
> > + return 0;
> > + if (prog_type != BPF_PROG_TYPE_XDP)
> > + return 0;
>
> Should this just handle XDP_METADATA_KFUNC_EXPORT_TO_SKB instead of
> passing that into the driver (to avoid every driver having to
> reimplement the same call to xdp_metadata_export_to_skb())?
Good idea, will try to move it here.
