From 9cacf81f8161111db25f98e78a7a0e32ae142b3f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:34:59 -0800 Subject: bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom call in do_tcp_getsockopt using the on-stack data. This removes 3% overhead for locking/unlocking the socket. Without this patch: 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc With the patch applied: 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern Note, exporting uapi/tcp.h requires removing netinet/tcp.h from test_progs.h because those headers have confliciting definitions. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com --- kernel/bpf/cgroup.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'kernel/bpf/cgroup.c') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 96555a8a2c54..416e7738981b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1486,6 +1486,52 @@ out: sockopt_free_buf(&ctx); return ret; } + +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_kern ctx = { + .sk = sk, + .level = level, + .optname = optname, + .retval = retval, + .optlen = *optlen, + .optval = optval, + .optval_end = optval + *optlen, + }; + int ret; + + /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy + * user data back into BPF buffer when reval != 0. This is + * done as an optimization to avoid extra copy, assuming + * kernel won't populate the data in case of an error. + * Here we always pass the data and memset() should + * be called if that data shouldn't be "exported". + */ + + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + &ctx, BPF_PROG_RUN); + if (!ret) + return -EPERM; + + if (ctx.optlen > *optlen) + return -EFAULT; + + /* BPF programs only allowed to set retval to 0, not some + * arbitrary value. + */ + if (ctx.retval != 0 && ctx.retval != retval) + return -EFAULT; + + /* BPF programs can shrink the buffer, export the modifications. + */ + if (ctx.optlen != 0) + *optlen = ctx.optlen; + + return ctx.retval; +} #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, -- cgit v1.2.3 From 20f2505fb436cfa674cf1f46aaa624f44d3d1d03 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:00 -0800 Subject: bpf: Try to avoid kzalloc in cgroup/{s,g}etsockopt When we attach a bpf program to cgroup/getsockopt any other getsockopt() syscall starts incurring kzalloc/kfree cost. Let add a small buffer on the stack and use it for small (majority) {s,g}etsockopt values. The buffer is small enough to fit into the cache line and cover the majority of simple options (most of them are 4 byte ints). 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. Without this patch (we remove about 1% __kmalloc): 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-3-sdf@google.com --- kernel/bpf/cgroup.c | 52 +++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 45 insertions(+), 7 deletions(-) (limited to 'kernel/bpf/cgroup.c') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 416e7738981b..ba8a1199d0ba 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1298,7 +1298,8 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, return empty; } -static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) +static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen, + struct bpf_sockopt_buf *buf) { if (unlikely(max_optlen < 0)) return -EINVAL; @@ -1310,6 +1311,15 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) max_optlen = PAGE_SIZE; } + if (max_optlen <= sizeof(buf->data)) { + /* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE + * bytes avoid the cost of kzalloc. + */ + ctx->optval = buf->data; + ctx->optval_end = ctx->optval + max_optlen; + return max_optlen; + } + ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; @@ -1319,16 +1329,26 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) return max_optlen; } -static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) +static void sockopt_free_buf(struct bpf_sockopt_kern *ctx, + struct bpf_sockopt_buf *buf) { + if (ctx->optval == buf->data) + return; kfree(ctx->optval); } +static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx, + struct bpf_sockopt_buf *buf) +{ + return ctx->optval != buf->data; +} + int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, int *optname, char __user *optval, int *optlen, char **kernel_optval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = *level, @@ -1350,7 +1370,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, */ max_optlen = max_t(int, 16, *optlen); - max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; @@ -1390,14 +1410,31 @@ 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, &buf)) { + void *p = kmalloc(ctx.optlen, GFP_USER); + + if (!p) { + ret = -ENOMEM; + goto out; + } + memcpy(p, ctx.optval, ctx.optlen); + *kernel_optval = p; + } else { + *kernel_optval = ctx.optval; + } /* export and don't free sockopt buf */ return 0; } } out: - sockopt_free_buf(&ctx); + sockopt_free_buf(&ctx, &buf); return ret; } @@ -1407,6 +1444,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int retval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = level, @@ -1425,7 +1463,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, ctx.optlen = max_optlen; - max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; @@ -1483,7 +1521,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, ret = ctx.retval; out: - sockopt_free_buf(&ctx); + sockopt_free_buf(&ctx, &buf); return ret; } -- cgit v1.2.3 From a9ed15dae0755a0368735e0556a462d8519bdb05 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:01 -0800 Subject: bpf: Split cgroup_bpf_enabled per attach type When we attach any cgroup hook, the rest (even if unused/unattached) start to contribute small overhead. In particular, the one we want to avoid is __cgroup_bpf_run_filter_skb which does two redirections to get to the cgroup and pushes/pulls skb. Let's split cgroup_bpf_enabled to be per-attach to make sure only used attach types trigger. I've dropped some existing high-level cgroup_bpf_enabled in some places because BPF_PROG_CGROUP_XXX_RUN macros usually have another cgroup_bpf_enabled check. I also had to copy-paste BPF_CGROUP_RUN_SA_PROG_LOCK for GETPEERNAME/GETSOCKNAME because type for cgroup_bpf_enabled[type] has to be constant and known at compile time. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210115163501.805133-4-sdf@google.com --- kernel/bpf/cgroup.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'kernel/bpf/cgroup.c') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ba8a1199d0ba..da649f20d6b2 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -19,7 +19,7 @@ #include "../cgroup/cgroup-internal.h" -DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key); +DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); void cgroup_bpf_offline(struct cgroup *cgrp) @@ -128,7 +128,7 @@ static void cgroup_bpf_release(struct work_struct *work) if (pl->link) bpf_cgroup_link_auto_detach(pl->link); kfree(pl); - static_branch_dec(&cgroup_bpf_enabled_key); + static_branch_dec(&cgroup_bpf_enabled_key[type]); } old_array = rcu_dereference_protected( cgrp->bpf.effective[type], @@ -499,7 +499,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, if (old_prog) bpf_prog_put(old_prog); else - static_branch_inc(&cgroup_bpf_enabled_key); + static_branch_inc(&cgroup_bpf_enabled_key[type]); bpf_cgroup_storages_link(new_storage, cgrp, type); return 0; @@ -698,7 +698,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, cgrp->bpf.flags[type] = 0; if (old_prog) bpf_prog_put(old_prog); - static_branch_dec(&cgroup_bpf_enabled_key); + static_branch_dec(&cgroup_bpf_enabled_key[type]); return 0; cleanup: @@ -1360,8 +1360,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, * attached to the hook so we don't waste time allocating * memory and locking the socket. */ - if (!cgroup_bpf_enabled || - __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) + if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) return 0; /* Allocate a bit more than the initial user buffer for @@ -1457,8 +1456,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, * attached to the hook so we don't waste time allocating * memory and locking the socket. */ - if (!cgroup_bpf_enabled || - __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) + if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) return retval; ctx.optlen = max_optlen; -- cgit v1.2.3 From 772412176fb98493158929b220fe250127f611af Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 27 Jan 2021 11:31:39 -0800 Subject: bpf: Allow rewriting to ports under ip_unprivileged_port_start At the moment, BPF_CGROUP_INET{4,6}_BIND hooks can rewrite user_port to the privileged ones (< ip_unprivileged_port_start), but it will be rejected later on in the __inet_bind or __inet6_bind. Let's add another return value to indicate that CAP_NET_BIND_SERVICE check should be ignored. Use the same idea as we currently use in cgroup/egress where bit #1 indicates CN. Instead, for cgroup/bind{4,6}, bit #1 indicates that CAP_NET_BIND_SERVICE should be bypassed. v5: - rename flags to be less confusing (Andrey Ignatov) - rework BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY to work on flags and accept BPF_RET_SET_CN (no behavioral changes) v4: - Add missing IPv6 support (Martin KaFai Lau) v3: - Update description (Martin KaFai Lau) - Fix capability restore in selftest (Martin KaFai Lau) v2: - Switch to explicit return code (Martin KaFai Lau) Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Reviewed-by: Martin KaFai Lau Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/20210127193140.3170382-1-sdf@google.com --- kernel/bpf/cgroup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/cgroup.c') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index da649f20d6b2..cdf3c7e611d9 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1055,6 +1055,8 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @uaddr: sockaddr struct provided by user * @type: The type of program to be exectuted * @t_ctx: Pointer to attach type specific context + * @flags: Pointer to u32 which contains higher bits of BPF program + * return value (OR'ed together). * * socket is expected to be of type INET or INET6. * @@ -1064,7 +1066,8 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, enum bpf_attach_type type, - void *t_ctx) + void *t_ctx, + u32 *flags) { struct bpf_sock_addr_kern ctx = { .sk = sk, @@ -1087,7 +1090,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + ret = BPF_PROG_RUN_ARRAY_FLAGS(cgrp->bpf.effective[type], &ctx, + BPF_PROG_RUN, flags); return ret == 1 ? 0 : -EPERM; } -- cgit v1.2.3