From dbe69b29988465b011f198f2797b1c2b6980b50e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 18 Oct 2022 09:59:34 +0200 Subject: bpf: Fix dispatcher patchable function entry to 5 bytes nop The patchable_function_entry(5) might output 5 single nop instructions (depends on toolchain), which will clash with bpf_arch_text_poke check for 5 bytes nop instruction. Adding early init call for dispatcher that checks and change the patchable entry into expected 5 nop instruction if needed. There's no need to take text_mutex, because we are using it in early init call which is called at pre-smp time. Fixes: ceea991a019c ("bpf: Move bpf_dispatcher function out of ftrace locations") Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20221018075934.574415-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9e7d46d16032..0566705c1d4e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -27,6 +27,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -970,6 +971,8 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); +int __init bpf_arch_init_dispatcher_early(void *ip); + #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ @@ -983,6 +986,13 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func }, \ } +#define BPF_DISPATCHER_INIT_CALL(_name) \ + static int __init _name##_init(void) \ + { \ + return bpf_arch_init_dispatcher_early(_name##_func); \ + } \ + early_initcall(_name##_init) + #ifdef CONFIG_X86_64 #define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5))) #else @@ -1000,7 +1010,9 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ - BPF_DISPATCHER_INIT(bpf_dispatcher_##name); + BPF_DISPATCHER_INIT(bpf_dispatcher_##name); \ + BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name); + #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ -- cgit v1.2.3 From 720ca52bcef225b967a339e0fffb6d0c7e962240 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 21 Oct 2022 09:03:04 -0700 Subject: net-memcg: avoid stalls when under memory pressure As Shakeel explains the commit under Fixes had the unintended side-effect of no longer pre-loading the cached memory allowance. Even tho we previously dropped the first packet received when over memory limit - the consecutive ones would get thru by using the cache. The charging was happening in batches of 128kB, so we'd let in 128kB (truesize) worth of packets per one drop. After the change we no longer force charge, there will be no cache filling side effects. This causes significant drops and connection stalls for workloads which use a lot of page cache, since we can't reclaim page cache under GFP_NOWAIT. Some of the latency can be recovered by improving SACK reneg handling but nowhere near enough to get back to the pre-5.15 performance (the application I'm experimenting with still sees 5-10x worst latency). Apply the suggested workaround of using GFP_ATOMIC. We will now be more permissive than previously as we'll drop _no_ packets in softirq when under pressure. But I can't think of any good and simple way to address that within networking. Link: https://lore.kernel.org/all/20221012163300.795e7b86@kernel.org/ Suggested-by: Shakeel Butt Fixes: 4b1327be9fe5 ("net-memcg: pass in gfp_t mask to mem_cgroup_charge_skmem()") Acked-by: Shakeel Butt Acked-by: Roman Gushchin Link: https://lore.kernel.org/r/20221021160304.1362511-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 9e464f6409a7..22f8bab583dd 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2585,7 +2585,7 @@ static inline gfp_t gfp_any(void) static inline gfp_t gfp_memcg_charge(void) { - return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; + return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) -- cgit v1.2.3