| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 7 Oct 2019 13:42:36 -0700
From: Alexei Starovoitov <alexei.starovoitov@...il.com>
To: Toke Høiland-Jørgensen <toke@...hat.com>
Cc: Daniel Borkmann <daniel@...earbox.net>,
Alexei Starovoitov <ast@...nel.org>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
Marek Majkowski <marek@...udflare.com>,
Lorenz Bauer <lmb@...udflare.com>,
Alan Maguire <alan.maguire@...cle.com>,
Jesper Dangaard Brouer <brouer@...hat.com>,
David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
bpf@...r.kernel.org
Subject: Re: [PATCH bpf-next v3 1/5] bpf: Support chain calling multiple BPF
programs after each other
On Mon, Oct 07, 2019 at 07:20:36PM +0200, Toke Høiland-Jørgensen wrote:
> From: Toke Høiland-Jørgensen <toke@...hat.com>
>
> This adds support for wrapping eBPF program dispatch in chain calling
> logic. The code injection is controlled by a flag at program load time; if
> the flag is set, the BPF program will carry a flag bit that changes the
> program dispatch logic to wrap it in a chain call loop.
>
> Ideally, it shouldn't be necessary to set the flag on program load time,
> but rather inject the calls when a chain call program is first loaded. The
> allocation logic sets the whole of struct bpf_prog to be read-only memory,
> so it can't immediately be modified, but conceivably we could just unlock
> the first page of the struct and flip the bit when a chain call program is
> first attached.
>
> Signed-off-by: Toke Høiland-Jørgensen <toke@...hat.com>
> ---
> include/linux/bpf.h | 3 +++
> include/linux/filter.h | 34 ++++++++++++++++++++++++++++++++--
> include/uapi/linux/bpf.h | 6 ++++++
> kernel/bpf/core.c | 6 ++++++
> kernel/bpf/syscall.c | 4 +++-
> 5 files changed, 50 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 5b9d22338606..13e5f38cf5c6 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -365,6 +365,8 @@ struct bpf_prog_stats {
> struct u64_stats_sync syncp;
> };
>
> +#define BPF_NUM_CHAIN_SLOTS 8
> +
> struct bpf_prog_aux {
> atomic_t refcnt;
> u32 used_map_cnt;
> @@ -383,6 +385,7 @@ struct bpf_prog_aux {
> struct list_head ksym_lnode;
> const struct bpf_prog_ops *ops;
> struct bpf_map **used_maps;
> + struct bpf_prog *chain_progs[BPF_NUM_CHAIN_SLOTS];
> struct bpf_prog *prog;
> struct user_struct *user;
> u64 load_time; /* ns since boottime */
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 2ce57645f3cd..3d1e4991e61d 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -21,6 +21,7 @@
> #include <linux/kallsyms.h>
> #include <linux/if_vlan.h>
> #include <linux/vmalloc.h>
> +#include <linux/nospec.h>
>
> #include <net/sch_generic.h>
>
> @@ -528,6 +529,7 @@ struct bpf_prog {
> is_func:1, /* program is a bpf function */
> kprobe_override:1, /* Do we override a kprobe? */
> has_callchain_buf:1, /* callchain buffer allocated? */
> + chain_calls:1, /* should this use the chain_call wrapper */
> enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */
> enum bpf_prog_type type; /* Type of BPF program */
> enum bpf_attach_type expected_attach_type; /* For some prog types */
> @@ -551,6 +553,30 @@ struct sk_filter {
> struct bpf_prog *prog;
> };
>
> +#define BPF_MAX_CHAIN_CALLS 32
> +static __always_inline unsigned int do_chain_calls(const struct bpf_prog *prog,
> + const void *ctx)
> +{
> + int i = BPF_MAX_CHAIN_CALLS;
> + int idx;
> + u32 ret;
> +
> + do {
> + ret = (*(prog)->bpf_func)(ctx, prog->insnsi);
This breaks program stats.
> +
> + if (ret + 1 >= BPF_NUM_CHAIN_SLOTS) {
> + prog = prog->aux->chain_progs[0];
> + continue;
> + }
> + idx = ret + 1;
> + idx = array_index_nospec(idx, BPF_NUM_CHAIN_SLOTS);
> +
> + prog = prog->aux->chain_progs[idx] ?: prog->aux->chain_progs[0];
> + } while (prog && --i);
> +
> + return ret;
> +}
> +
> DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
>
> #define BPF_PROG_RUN(prog, ctx) ({ \
> @@ -559,14 +585,18 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
> if (static_branch_unlikely(&bpf_stats_enabled_key)) { \
> struct bpf_prog_stats *stats; \
> u64 start = sched_clock(); \
> - ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \
> + ret = prog->chain_calls ? \
> + do_chain_calls(prog, ctx) : \
> + (*(prog)->bpf_func)(ctx, (prog)->insnsi); \
I thought you agreed on 'no performance regressions' rule?
> stats = this_cpu_ptr(prog->aux->stats); \
> u64_stats_update_begin(&stats->syncp); \
> stats->cnt++; \
> stats->nsecs += sched_clock() - start; \
> u64_stats_update_end(&stats->syncp); \
> } else { \
> - ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \
> + ret = prog->chain_calls ? \
> + do_chain_calls(prog, ctx) : \
> + (*(prog)->bpf_func)(ctx, (prog)->insnsi); \
> } \
> ret; })
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 77c6be96d676..1ce80a227be3 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -288,6 +288,12 @@ enum bpf_attach_type {
> /* The verifier internal test flag. Behavior is undefined */
> #define BPF_F_TEST_STATE_FREQ (1U << 3)
>
> +/* Whether to enable chain call logic at program execution. If set, the program
> + * execution logic will check for and jump to chain call programs configured
> + * with the BPF_PROG_CHAIN_* commands to the bpf syscall.
> + */
> +#define BPF_F_CHAIN_CALLS (1U << 4)
> +
> /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
> * two extensions:
> *
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index 66088a9e9b9e..5dfe3585bc5d 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -254,6 +254,12 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
> void __bpf_prog_free(struct bpf_prog *fp)
> {
> if (fp->aux) {
> + int i;
> +
> + for (i = 0; i < BPF_NUM_CHAIN_SLOTS; i++)
> + if (fp->aux->chain_progs[i])
> + bpf_prog_put(fp->aux->chain_progs[i]);
> +
> free_percpu(fp->aux->stats);
> kfree(fp->aux);
> }
> diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> index 82eabd4e38ad..b8a203a05881 100644
> --- a/kernel/bpf/syscall.c
> +++ b/kernel/bpf/syscall.c
> @@ -1630,7 +1630,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
> if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT |
> BPF_F_ANY_ALIGNMENT |
> BPF_F_TEST_STATE_FREQ |
> - BPF_F_TEST_RND_HI32))
> + BPF_F_TEST_RND_HI32 |
> + BPF_F_CHAIN_CALLS))
> return -EINVAL;
>
> if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
> @@ -1665,6 +1666,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
> return -ENOMEM;
>
> prog->expected_attach_type = attr->expected_attach_type;
> + prog->chain_calls = !!(attr->prog_flags & BPF_F_CHAIN_CALLS);
>
> prog->aux->offload_requested = !!attr->prog_ifindex;
>
>
Powered by blists - more mailing lists