From 4976b718c3551faba2c0616ef55ebeb74db1c5ca Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 29 Sep 2020 16:50:44 -0700 Subject: bpf: Introduce pseudo_btf_id Pseudo_btf_id is a type of ld_imm insn that associates a btf_id to a ksym so that further dereferences on the ksym can use the BTF info to validate accesses. Internally, when seeing a pseudo_btf_id ld insn, the verifier reads the btf_id stored in the insn[0]'s imm field and marks the dst_reg as PTR_TO_BTF_ID. The btf_id points to a VAR_KIND, which is encoded in btf_vminux by pahole. If the VAR is not of a struct type, the dst reg will be marked as PTR_TO_MEM instead of PTR_TO_BTF_ID and the mem_size is resolved to the size of the VAR's type. >From the VAR btf_id, the verifier can also read the address of the ksym's corresponding kernel var from kallsyms and use that to fill dst_reg. Therefore, the proper functionality of pseudo_btf_id depends on (1) kallsyms and (2) the encoding of kernel global VARs in pahole, which should be available since pahole v1.18. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200929235049.2533242-2-haoluo@google.com --- include/uapi/linux/bpf.h | 36 +++++++++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4f556cfcbfbe..2aa156af24d6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -356,18 +356,36 @@ enum bpf_link_type { #define BPF_F_SLEEPABLE (1U << 4) /* When BPF ldimm64's insn[0].src_reg != 0 then this can have - * two extensions: - * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd map fd - * insn[1].imm: 0 offset into value - * insn[0].off: 0 0 - * insn[1].off: 0 0 - * ldimm64 rewrite: address of map address of map[0]+offset - * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE + * the following extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_FD + * insn[0].imm: map fd + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map + * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 +/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE + * insn[0].imm: map fd + * insn[1].imm: offset into value + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map[0]+offset + * verifier type: PTR_TO_MAP_VALUE + */ #define BPF_PSEUDO_MAP_VALUE 2 +/* insn[0].src_reg: BPF_PSEUDO_BTF_ID + * insn[0].imm: kernel btd id of VAR + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of the kernel variable + * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var + * is struct/union. + */ +#define BPF_PSEUDO_BTF_ID 3 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function -- cgit v1.2.3 From eaa6bcb71ef6ed3dc18fc525ee7e293b06b4882b Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 29 Sep 2020 16:50:47 -0700 Subject: bpf: Introduce bpf_per_cpu_ptr() Add bpf_per_cpu_ptr() to help bpf programs access percpu vars. bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the kernel except that it may return NULL. This happens when the cpu parameter is out of range. So the caller must check the returned value. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200929235049.2533242-5-haoluo@google.com --- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2aa156af24d6..f3c1b637ab39 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3686,6 +3686,23 @@ union bpf_attr { * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. + * + * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on *cpu*. A ksym is an + * extern variable decorated with '__ksym'. For ksym, there is a + * global var (either static or global) defined of the same name + * in the kernel. The ksym is percpu if the global var is percpu. + * The returned pointer points to the global percpu var on *cpu*. + * + * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the + * kernel, except that bpf_per_cpu_ptr() may return NULL. This + * happens if *cpu* is larger than nr_cpu_ids. The caller of + * bpf_per_cpu_ptr() must check the returned value. + * Return + * A pointer pointing to the kernel percpu variable on *cpu*, or + * NULL, if *cpu* is invalid. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3841,6 +3858,7 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ + FN(bpf_per_cpu_ptr), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 63d9b80dcf2c67bc5ade61cbbaa09d7af21f43f1 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 29 Sep 2020 16:50:48 -0700 Subject: bpf: Introducte bpf_this_cpu_ptr() Add bpf_this_cpu_ptr() to help access percpu var on this cpu. This helper always returns a valid pointer, therefore no need to check returned value for NULL. Also note that all programs run with preemption disabled, which means that the returned pointer is stable during all the execution of the program. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200929235049.2533242-6-haoluo@google.com --- include/uapi/linux/bpf.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f3c1b637ab39..c446394135be 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3703,6 +3703,18 @@ union bpf_attr { * Return * A pointer pointing to the kernel percpu variable on *cpu*, or * NULL, if *cpu* is invalid. + * + * void *bpf_this_cpu_ptr(const void *percpu_ptr) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on this cpu. See the + * description of 'ksym' in **bpf_per_cpu_ptr**\ (). + * + * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in + * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would + * never return NULL. + * Return + * A pointer pointing to the kernel percpu variable on this cpu. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3859,6 +3871,7 @@ union bpf_attr { FN(skb_cgroup_classid), \ FN(redirect_neigh), \ FN(bpf_per_cpu_ptr), \ + FN(bpf_this_cpu_ptr), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 49f3d12b0f70ea867b891ad2a97f6e51bb564e18 Mon Sep 17 00:00:00 2001 From: Jakub Wilk Date: Wed, 7 Oct 2020 07:57:17 +0200 Subject: bpf: Fix typo in uapi/linux/bpf.h Reported-by: Samanta Navarro Signed-off-by: Jakub Wilk Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201007055717.7319-1-jwilk@jwilk.net --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c446394135be..d83561e8cd2c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2253,7 +2253,7 @@ union bpf_attr { * Description * This helper is used in programs implementing policies at the * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. - * if the verdeict eBPF program returns **SK_PASS**), redirect it + * if the verdict eBPF program returns **SK_PASS**), redirect it * to the socket referenced by *map* (of type * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and * egress interfaces can be used for redirection. The -- cgit v1.2.3 From eca43ee6c46db92dd850ce659316b0680d70e137 Mon Sep 17 00:00:00 2001 From: "Nikita V. Shirokov" Date: Fri, 9 Oct 2020 07:03:25 +0000 Subject: bpf: Add tcp_notsent_lowat bpf setsockopt Adding support for TCP_NOTSENT_LOWAT sockoption (https://lwn.net/Articles/560082/) in tcp bpf programs. Signed-off-by: Nikita V. Shirokov Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201009070325.226855-1-tehnerd@tehnerd.com --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d83561e8cd2c..42d2df799397 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1698,7 +1698,7 @@ union bpf_attr { * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return -- cgit v1.2.3 From dd2ce6a5373c6f5c830be54be10775458a8bd312 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 11 Oct 2020 01:40:01 +0200 Subject: bpf: Improve bpf_redirect_neigh helper description Follow-up to address David's feedback that we should better describe internals of the bpf_redirect_neigh() helper. Suggested-by: David Ahern Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Reviewed-by: David Ahern Link: https://lore.kernel.org/bpf/20201010234006.7075-2-daniel@iogearbox.net --- include/uapi/linux/bpf.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 42d2df799397..4272cc53d478 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3679,10 +3679,14 @@ union bpf_attr { * Redirect the packet to another net device of index *ifindex* * and fill in L2 addresses from neighboring subsystem. This helper * is somewhat similar to **bpf_redirect**\ (), except that it - * fills in e.g. MAC addresses based on the L3 information from - * the packet. This helper is supported for IPv4 and IPv6 protocols. + * populates L2 addresses as well, meaning, internally, the helper + * performs a FIB lookup based on the skb's networking header to + * get the address of the next hop and then relies on the neighbor + * lookup for the L2 address of the nexthop. + * * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types. + * currently only supported for tc BPF program types, and enabled + * for IPv4 and IPv6 protocols. * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. -- cgit v1.2.3 From 9aa1206e8f48222f35a0c809f33b2f4aaa1e2661 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 11 Oct 2020 01:40:02 +0200 Subject: bpf: Add redirect_peer helper Add an efficient ingress to ingress netns switch that can be used out of tc BPF programs in order to redirect traffic from host ns ingress into a container veth device ingress without having to go via CPU backlog queue [0]. For local containers this can also be utilized and path via CPU backlog queue only needs to be taken once, not twice. On a high level this borrows from ipvlan which does similar switch in __netif_receive_skb_core() and then iterates via another_round. This helps to reduce latency for mentioned use cases. Pod to remote pod with redirect(), TCP_RR [1]: # percpu_netperf 10.217.1.33 RT_LATENCY: 122.450 (per CPU: 122.666 122.401 122.333 122.401 ) MEAN_LATENCY: 121.210 (per CPU: 121.100 121.260 121.320 121.160 ) STDDEV_LATENCY: 120.040 (per CPU: 119.420 119.910 125.460 115.370 ) MIN_LATENCY: 46.500 (per CPU: 47.000 47.000 47.000 45.000 ) P50_LATENCY: 118.500 (per CPU: 118.000 119.000 118.000 119.000 ) P90_LATENCY: 127.500 (per CPU: 127.000 128.000 127.000 128.000 ) P99_LATENCY: 130.750 (per CPU: 131.000 131.000 129.000 132.000 ) TRANSACTION_RATE: 32666.400 (per CPU: 8152.200 8169.842 8174.439 8169.897 ) Pod to remote pod with redirect_peer(), TCP_RR: # percpu_netperf 10.217.1.33 RT_LATENCY: 44.449 (per CPU: 43.767 43.127 45.279 45.622 ) MEAN_LATENCY: 45.065 (per CPU: 44.030 45.530 45.190 45.510 ) STDDEV_LATENCY: 84.823 (per CPU: 66.770 97.290 84.380 90.850 ) MIN_LATENCY: 33.500 (per CPU: 33.000 33.000 34.000 34.000 ) P50_LATENCY: 43.250 (per CPU: 43.000 43.000 43.000 44.000 ) P90_LATENCY: 46.750 (per CPU: 46.000 47.000 47.000 47.000 ) P99_LATENCY: 52.750 (per CPU: 51.000 54.000 53.000 53.000 ) TRANSACTION_RATE: 90039.500 (per CPU: 22848.186 23187.089 22085.077 21919.130 ) [0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf [1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net --- include/uapi/linux/bpf.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4272cc53d478..b97bc5abb3b8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3719,6 +3719,22 @@ union bpf_attr { * never return NULL. * Return * A pointer pointing to the kernel percpu variable on this cpu. + * + * long bpf_redirect_peer(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_redirect**\ (), except + * that the redirection happens to the *ifindex*' peer device and + * the netns switch takes place from ingress to ingress without + * going through the CPU's backlog queue. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types at the ingress + * hook and for veth device types. The peer device must reside in a + * different network namespace. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3876,6 +3892,7 @@ union bpf_attr { FN(redirect_neigh), \ FN(bpf_per_cpu_ptr), \ FN(bpf_this_cpu_ptr), \ + FN(redirect_peer), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 4a8f87e60f6db40e640f1db555d063b2c4dea5f1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 11 Oct 2020 01:40:03 +0200 Subject: bpf: Allow for map-in-map with dynamic inner array map entries Recent work in f4d05259213f ("bpf: Add map_meta_equal map ops") and 134fede4eecf ("bpf: Relax max_entries check for most of the inner map types") added support for dynamic inner max elements for most map-in-map types. Exceptions were maps like array or prog array where the map_gen_lookup() callback uses the maps' max_entries field as a constant when emitting instructions. We recently implemented Maglev consistent hashing into Cilium's load balancer which uses map-in-map with an outer map being hash and inner being array holding the Maglev backend table for each service. This has been designed this way in order to reduce overall memory consumption given the outer hash map allows to avoid preallocating a large, flat memory area for all services. Also, the number of service mappings is not always known a-priori. The use case for dynamic inner array map entries is to further reduce memory overhead, for example, some services might just have a small number of back ends while others could have a large number. Right now the Maglev backend table for small and large number of backends would need to have the same inner array map entries which adds a lot of unneeded overhead. Dynamic inner array map entries can be realized by avoiding the inlined code generation for their lookup. The lookup will still be efficient since it will be calling into array_map_lookup_elem() directly and thus avoiding retpoline. The patch adds a BPF_F_INNER_MAP flag to map creation which therefore skips inline code generation and relaxes array_map_meta_equal() check to ignore both maps' max_entries. This also still allows to have faster lookups for map-in-map when BPF_F_INNER_MAP is not specified and hence dynamic max_entries not needed. Example code generation where inner map is dynamic sized array: # bpftool p d x i 125 int handle__sys_enter(void * ctx): ; int handle__sys_enter(void *ctx) 0: (b4) w1 = 0 ; int key = 0; 1: (63) *(u32 *)(r10 -4) = r1 2: (bf) r2 = r10 ; 3: (07) r2 += -4 ; inner_map = bpf_map_lookup_elem(&outer_arr_dyn, &key); 4: (18) r1 = map[id:468] 6: (07) r1 += 272 7: (61) r0 = *(u32 *)(r2 +0) 8: (35) if r0 >= 0x3 goto pc+5 9: (67) r0 <<= 3 10: (0f) r0 += r1 11: (79) r0 = *(u64 *)(r0 +0) 12: (15) if r0 == 0x0 goto pc+1 13: (05) goto pc+1 14: (b7) r0 = 0 15: (b4) w6 = -1 ; if (!inner_map) 16: (15) if r0 == 0x0 goto pc+6 17: (bf) r2 = r10 ; 18: (07) r2 += -4 ; val = bpf_map_lookup_elem(inner_map, &key); 19: (bf) r1 = r0 | No inlining but instead 20: (85) call array_map_lookup_elem#149280 | call to array_map_lookup_elem() ; return val ? *val : -1; | for inner array lookup. 21: (15) if r0 == 0x0 goto pc+1 ; return val ? *val : -1; 22: (61) r6 = *(u32 *)(r0 +0) ; } 23: (bc) w0 = w6 24: (95) exit Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201010234006.7075-4-daniel@iogearbox.net --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b97bc5abb3b8..bf5a99d803e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -435,6 +435,9 @@ enum { /* Share perf_event among processes */ BPF_F_PRESERVE_ELEMS = (1U << 11), + +/* Create a map that is suitable to be an inner map with dynamic max entries */ + BPF_F_INNER_MAP = (1U << 12), }; /* Flags for BPF_PROG_QUERY. */ -- cgit v1.2.3