@@ -1281,6 +1281,8 @@ struct bpf_sysctl_kern {
u64 tmp_reg;
};
+#define BPF_SOCKOPT_KERN_BUF_SIZE 64
+
struct bpf_sockopt_kern {
struct sock *sk;
u8 *optval;
@@ -1289,6 +1291,7 @@ struct bpf_sockopt_kern {
s32 optname;
s32 optlen;
s32 retval;
+ u8 buf[BPF_SOCKOPT_KERN_BUF_SIZE];
};
int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
@@ -16,6 +16,7 @@
#include <linux/bpf-cgroup.h>
#include <net/sock.h>
#include <net/bpf_sk_storage.h>
+#include <uapi/linux/tcp.h> /* sizeof(struct tcp_zerocopy_receive) */
#include "../cgroup/cgroup-internal.h"
@@ -1310,6 +1311,22 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
max_optlen = PAGE_SIZE;
}
+ if (max_optlen <= sizeof(ctx->buf)) {
+ /* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE
+ * bytes avoid the cost of kzalloc.
+ *
+ * In order to remove extra allocations from the TCP
+ * fast zero-copy path ensure that buffer covers
+ * the size of struct tcp_zerocopy_receive.
+ */
+ BUILD_BUG_ON(sizeof(struct tcp_zerocopy_receive) >
+ BPF_SOCKOPT_KERN_BUF_SIZE);
+
+ ctx->optval = ctx->buf;
+ ctx->optval_end = ctx->optval + max_optlen;
+ return max_optlen;
+ }
+
ctx->optval = kzalloc(max_optlen, GFP_USER);
if (!ctx->optval)
return -ENOMEM;
@@ -1321,9 +1338,16 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
{
+ if (ctx->optval == ctx->buf)
+ return;
kfree(ctx->optval);
}
+static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx)
+{
+ return ctx->optval != ctx->buf;
+}
+
int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
int *optname, char __user *optval,
int *optlen, char **kernel_optval)
@@ -1390,7 +1414,24 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
*/
if (ctx.optlen != 0) {
*optlen = ctx.optlen;
- *kernel_optval = ctx.optval;
+ /* We've used bpf_sockopt_kern->buf as an intermediary
+ * storage, but the BPF program indicates that we need
+ * to pass this data to the kernel setsockopt handler.
+ * No way to export on-stack buf, have to allocate a
+ * new buffer.
+ */
+ if (!sockopt_buf_allocated(&ctx)) {
+ void *p = kzalloc(ctx.optlen, GFP_USER);
+
+ if (!p) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ memcpy(p, ctx.optval, ctx.optlen);
+ *kernel_optval = p;
+ } else {
+ *kernel_optval = ctx.optval;
+ }
}
}
When we attach a bpf program to cgroup/getsockopt any other getsockopt() syscall starts incurring kzalloc/kfree cost. While, in general, it's not an issue, sometimes it is, like in the case of TCP_ZEROCOPY_RECEIVE. TCP_ZEROCOPY_RECEIVE (ab)uses getsockopt system call to implement fastpath for incoming TCP, we don't want to have extra allocations in there. Let add a small buffer on the stack and use it for small (majority) {s,g}etsockopt values. I've started with 128 bytes to cover the options we care about (TCP_ZEROCOPY_RECEIVE which is 32 bytes currently, with some planned extension to 64). It seems natural to do the same for setsockopt, but it's a bit more involved when the BPF program modifies the data (where we have to kmalloc). The assumption is that for the majority of setsockopt calls (which are doing pure BPF options or apply policy) this will bring some benefit as well. Collected some performance numbers using (on a 65k MTU localhost in a VM): $ perf record -g -- ./tcp_mmap -s -z $ ./tcp_mmap -H ::1 -z $ ... $ perf report --symbol-filter=__cgroup_bpf_run_filter_getsockopt Without this patch: 4.81% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_> | --4.74%--__cgroup_bpf_run_filter_getsockopt | |--1.06%--__kmalloc | |--0.71%--lock_sock_nested | |--0.62%--__might_fault | --0.52%--release_sock With the patch applied: 3.29% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.22%--__cgroup_bpf_run_filter_getsockopt | |--0.66%--lock_sock_nested | |--0.57%--__might_fault | --0.56%--release_sock So it saves about 1% of the system call. Unfortunately, we still get 2-3% of overhead due to another socket lock/unlock :-( Signed-off-by: Stanislav Fomichev <sdf@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Song Liu <songliubraving@fb.com> --- include/linux/filter.h | 3 +++ kernel/bpf/cgroup.c | 43 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 1 deletion(-)