From 94dacdbd5d2dfa2cffd308f128d78c99f855f5be Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:32 +0100 Subject: bpf: Tighten the requirements for preallocated hash maps The assumption that only programs attached to perf NMI events can deadlock on memory allocators is wrong. Assume the following simplified callchain: kmalloc() from regular non BPF context cache empty freelist empty lock(zone->lock); tracepoint or kprobe BPF() update_elem() lock(bucket) kmalloc() cache empty freelist empty lock(zone->lock); <- DEADLOCK There are other ways which do not involve locking to create wreckage: kmalloc() from regular non BPF context local_irq_save(); ... obj = slab_first(); kprobe() BPF() update_elem() lock(bucket) kmalloc() local_irq_save(); ... obj = slab_first(); <- Same object as above ... So preallocation _must_ be enforced for all variants of intrusive instrumentation. Unfortunately immediate enforcement would break backwards compatibility, so for now such programs still are allowed to run, but a one time warning is emitted in dmesg and the verifier emits a warning in the verifier log as well so developers are made aware about this and can fix their programs before the enforcement becomes mandatory. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145642.540542802@linutronix.de --- kernel/bpf/verifier.c | 39 ++++++++++++++++++++++++++++----------- 1 file changed, 28 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6d15dfbd4b88..532b7b0320ba 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8143,26 +8143,43 @@ static bool is_tracing_prog_type(enum bpf_prog_type type) } } +static bool is_preallocated_map(struct bpf_map *map) +{ + if (!check_map_prealloc(map)) + return false; + if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) + return false; + return true; +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) { - /* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use - * preallocated hash maps, since doing memory allocation - * in overflow_handler can crash depending on where nmi got - * triggered. + /* + * Validate that trace type programs use preallocated hash maps. + * + * For programs attached to PERF events this is mandatory as the + * perf NMI can hit any arbitrary code sequence. + * + * All other trace types using preallocated hash maps are unsafe as + * well because tracepoint or kprobes can be inside locked regions + * of the memory allocator or at a place where a recursion into the + * memory allocator would see inconsistent state. + * + * For now running such programs is allowed for backwards + * compatibility reasons, but warnings are emitted so developers are + * made aware of the unsafety and can fix their programs before this + * is enforced. */ - if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { - if (!check_map_prealloc(map)) { + if (is_tracing_prog_type(prog->type) && !is_preallocated_map(map)) { + if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } - if (map->inner_map_meta && - !check_map_prealloc(map->inner_map_meta)) { - verbose(env, "perf_event programs can only use preallocated inner hash map\n"); - return -EINVAL; - } + WARN_ONCE(1, "trace type BPF program uses run-time allocation\n"); + verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n"); } if ((is_tracing_prog_type(prog->type) || -- cgit v1.2.3 From 2ed905c521e56aead6987df94c083efb0ee59895 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:33 +0100 Subject: bpf: Enforce preallocation for instrumentation programs on RT Aside of the general unsafety of run-time map allocation for instrumentation type programs RT enabled kernels have another constraint: The instrumentation programs are invoked with preemption disabled, but the memory allocator spinlocks cannot be acquired in atomic context because they are converted to 'sleeping' spinlocks on RT. Therefore enforce map preallocation for these programs types when RT is enabled. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145642.648784007@linutronix.de --- kernel/bpf/verifier.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 532b7b0320ba..289383edfc8c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8168,16 +8168,21 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, * of the memory allocator or at a place where a recursion into the * memory allocator would see inconsistent state. * - * For now running such programs is allowed for backwards - * compatibility reasons, but warnings are emitted so developers are - * made aware of the unsafety and can fix their programs before this - * is enforced. + * On RT enabled kernels run-time allocation of all trace type + * programs is strictly prohibited due to lock type constraints. On + * !RT kernels it is allowed for backwards compatibility reasons for + * now, but warnings are emitted so developers are made aware of + * the unsafety and can fix their programs before this is enforced. */ if (is_tracing_prog_type(prog->type) && !is_preallocated_map(map)) { if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + verbose(env, "trace type programs can only use preallocated hash map\n"); + return -EINVAL; + } WARN_ONCE(1, "trace type BPF program uses run-time allocation\n"); verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n"); } -- cgit v1.2.3 From dbca151cad736c99f4817076daf9fd02ed0c2daa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:34 +0100 Subject: bpf: Update locking comment in hashtab code The comment where the bucket lock is acquired says: /* bpf_map_update_elem() can be called in_irq() */ which is not really helpful and aside of that it does not explain the subtle details of the hash bucket locks expecially in the context of BPF and perf, kprobes and tracing. Add a comment at the top of the file which explains the protection scopes and the details how potential deadlocks are prevented. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145642.755793061@linutronix.de --- kernel/bpf/hashtab.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a1468e3f5af2..65711a220fe0 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -27,6 +27,26 @@ .map_delete_batch = \ generic_map_delete_batch +/* + * The bucket lock has two protection scopes: + * + * 1) Serializing concurrent operations from BPF programs on differrent + * CPUs + * + * 2) Serializing concurrent operations from BPF programs and sys_bpf() + * + * BPF programs can execute in any context including perf, kprobes and + * tracing. As there are almost no limits where perf, kprobes and tracing + * can be invoked from the lock operations need to be protected against + * deadlocks. Deadlocks can be caused by recursion and by an invocation in + * the lock held section when functions which acquire this lock are invoked + * from sys_bpf(). BPF recursion is prevented by incrementing the per CPU + * variable bpf_prog_active, which prevents BPF programs attached to perf + * events, kprobes and tracing to be invoked before the prior invocation + * from one of these contexts completed. sys_bpf() uses the same mechanism + * by pinning the task to the current CPU and incrementing the recursion + * protection accross the map operation. + */ struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -884,7 +904,6 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, */ } - /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -964,7 +983,6 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, return -ENOMEM; memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); - /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1019,7 +1037,6 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1083,7 +1100,6 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, return -ENOMEM; } - /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); -- cgit v1.2.3 From f03efe49bd16c017107ff5079d08ea428e390dde Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:35 +0100 Subject: bpf/tracing: Remove redundant preempt_disable() in __bpf_trace_run() __bpf_trace_run() disables preemption around the BPF_PROG_RUN() invocation. This is redundant because __bpf_trace_run() is invoked from a trace point via __DO_TRACE() which already disables preemption _before_ invoking any of the functions which are attached to a trace point. Remove it and add a cant_sleep() check. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145642.847220186@linutronix.de --- kernel/trace/bpf_trace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b8661bd0d028..4d42a5d05ec9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1516,10 +1516,9 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static __always_inline void __bpf_trace_run(struct bpf_prog *prog, u64 *args) { + cant_sleep(); rcu_read_lock(); - preempt_disable(); (void) BPF_PROG_RUN(prog, args); - preempt_enable(); rcu_read_unlock(); } -- cgit v1.2.3 From 1b7a51a63b031092b8b8acda3f6820b62a8b5e5d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:36 +0100 Subject: bpf/trace: Remove EXPORT from trace_call_bpf() All callers are built in. No point to export this. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4d42a5d05ec9..15fafaed027c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -119,7 +119,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) return ret; } -EXPORT_SYMBOL_GPL(trace_call_bpf); #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) -- cgit v1.2.3 From 70ed0706a48e3da3eb4515214fef658ff1184b9f Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 24 Feb 2020 11:27:15 -0800 Subject: bpf: disable preemption for bpf progs attached to uprobe trace_call_bpf() no longer disables preemption on its own. All callers of this function has to do it explicitly. Signed-off-by: Alexei Starovoitov Acked-by: Thomas Gleixner --- kernel/trace/trace_uprobe.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 18d16f3ef980..2a8e8e9c1c75 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1333,8 +1333,15 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, int size, esize; int rctx; - if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) - return; + if (bpf_prog_array_valid(call)) { + u32 ret; + + preempt_disable(); + ret = trace_call_bpf(call, regs); + preempt_enable(); + if (!ret) + return; + } esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); -- cgit v1.2.3 From b0a81b94cc50a112601721fcc2f91fab78d7b9f3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:37 +0100 Subject: bpf/trace: Remove redundant preempt_disable from trace_call_bpf() Similar to __bpf_trace_run this is redundant because __bpf_trace_run() is invoked from a trace point via __DO_TRACE() which already disables preemption _before_ invoking any of the functions which are attached to a trace point. Remove it and add a cant_sleep() check. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145643.059995527@linutronix.de --- kernel/trace/bpf_trace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 15fafaed027c..07764c761073 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -83,7 +83,7 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) if (in_nmi()) /* not supported yet */ return 1; - preempt_disable(); + cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* @@ -115,7 +115,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) out: __this_cpu_dec(bpf_prog_active); - preempt_enable(); return ret; } -- cgit v1.2.3 From 1d7bf6b7d3e8353c3fac648f3f9b3010458570c2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:38 +0100 Subject: perf/bpf: Remove preempt disable around BPF invocation The BPF invocation from the perf event overflow handler does not require to disable preemption because this is called from NMI or at least hard interrupt context which is already non-preemptible. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145643.151953573@linutronix.de --- kernel/events/core.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index e453589da97c..bbdfac0182f4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9206,7 +9206,6 @@ static void bpf_overflow_handler(struct perf_event *event, int ret = 0; ctx.regs = perf_arch_bpf_user_pt_regs(regs); - preempt_disable(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) goto out; rcu_read_lock(); @@ -9214,7 +9213,6 @@ static void bpf_overflow_handler(struct perf_event *event, rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); - preempt_enable(); if (!ret) return; -- cgit v1.2.3 From 8a37963c7ac9ecb7f86f8ebda020e3f8d6d7b8a0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:39 +0100 Subject: bpf: Remove recursion prevention from rcu free callback If an element is freed via RCU then recursion into BPF instrumentation functions is not a concern. The element is already detached from the map and the RCU callback does not hold any locks on which a kprobe, perf event or tracepoint attached BPF program could deadlock. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145643.259118710@linutronix.de --- kernel/bpf/hashtab.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 65711a220fe0..431cef22d29d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -706,15 +706,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab; - /* must increment bpf_prog_active to avoid kprobe+bpf triggering while - * we're calling kfree, otherwise deadlock is possible if kprobes - * are placed somewhere inside of slub - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); htab_elem_free(htab, l); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); } static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) -- cgit v1.2.3 From 569de905ebc30b9c61be7aa557403aeb5a9141a4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:40 +0100 Subject: bpf: Dont iterate over possible CPUs with interrupts disabled pcpu_freelist_populate() is disabling interrupts and then iterates over the possible CPUs. The reason why this disables interrupts is to silence lockdep because the invoked ___pcpu_freelist_push() takes spin locks. Neither the interrupt disabling nor the locking are required in this function because it's called during initialization and the resulting map is not yet visible to anything. Split out the actual push assignement into an inline, call it from the loop and remove the interrupt disable. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145643.365930116@linutronix.de --- kernel/bpf/percpu_freelist.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 6e090140b924..b367430e611c 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -25,12 +25,18 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } +static inline void pcpu_freelist_push_node(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) +{ + node->next = head->first; + head->first = node; +} + static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); - node->next = head->first; - head->first = node; + pcpu_freelist_push_node(head, node); raw_spin_unlock(&head->lock); } @@ -56,21 +62,16 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems) { struct pcpu_freelist_head *head; - unsigned long flags; int i, cpu, pcpu_entries; pcpu_entries = nr_elems / num_possible_cpus() + 1; i = 0; - /* disable irq to workaround lockdep false positive - * in bpf usage pcpu_freelist_populate() will never race - * with pcpu_freelist_push() - */ - local_irq_save(flags); for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - ___pcpu_freelist_push(head, buf); + /* No locking required as this is not visible yet. */ + pcpu_freelist_push_node(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -78,7 +79,6 @@ again: if (i % pcpu_entries) goto again; } - local_irq_restore(flags); } struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) -- cgit v1.2.3 From 3d9f773cf2876c01a505b9fe27270901d464e90a Mon Sep 17 00:00:00 2001 From: David Miller Date: Mon, 24 Feb 2020 15:01:43 +0100 Subject: bpf: Use bpf_prog_run_pin_on_cpu() at simple call sites. All of these cases are strictly of the form: preempt_disable(); BPF_PROG_RUN(...); preempt_enable(); Replace this with bpf_prog_run_pin_on_cpu() which wraps BPF_PROG_RUN() with: migrate_disable(); BPF_PROG_RUN(...); migrate_enable(); On non RT enabled kernels this maps to preempt_disable/enable() and on RT enabled kernels this solely prevents migration, which is sufficient as there is no requirement to prevent reentrancy to any BPF program from a preempting task. The only requirement is that the program stays on the same CPU. Therefore, this is a trivially correct transformation. The seccomp loop does not need protection over the loop. It only needs protection per BPF filter program [ tglx: Converted to bpf_prog_run_pin_on_cpu() ] Signed-off-by: David S. Miller Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145643.691493094@linutronix.de --- include/linux/filter.h | 4 +--- kernel/seccomp.c | 4 +--- net/core/flow_dissector.c | 4 +--- net/core/skmsg.c | 8 ++------ net/kcm/kcmsock.c | 4 +--- 5 files changed, 6 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1982a52eb4c9..9270de2a0df8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -717,9 +717,7 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - preempt_disable(); - res = BPF_PROG_RUN(prog, skb); - preempt_enable(); + res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index b6ea3dcb57bf..787041eb011b 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -268,16 +268,14 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ - preempt_disable(); for (; f; f = f->prev) { - u32 cur_ret = BPF_PROG_RUN(f->prog, sd); + u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } - preempt_enable(); return ret; } #endif /* CONFIG_SECCOMP_FILTER */ diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a1670dff0629..3eff84824c8b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -920,9 +920,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; - preempt_disable(); - result = BPF_PROG_RUN(prog, ctx); - preempt_enable(); + result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, diff --git a/net/core/skmsg.c b/net/core/skmsg.c index eeb28cb85664..c479372f2cd2 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -628,7 +628,6 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct bpf_prog *prog; int ret; - preempt_disable(); rcu_read_lock(); prog = READ_ONCE(psock->progs.msg_parser); if (unlikely(!prog)) { @@ -638,7 +637,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, sk_msg_compute_data_pointers(msg); msg->sk = sk; - ret = BPF_PROG_RUN(prog, msg); + ret = bpf_prog_run_pin_on_cpu(prog, msg); ret = sk_psock_map_verd(ret, msg->sk_redir); psock->apply_bytes = msg->apply_bytes; if (ret == __SK_REDIRECT) { @@ -653,7 +652,6 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, } out: rcu_read_unlock(); - preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); @@ -665,9 +663,7 @@ static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, skb->sk = psock->sk; bpf_compute_data_end_sk_skb(skb); - preempt_disable(); - ret = BPF_PROG_RUN(prog, skb); - preempt_enable(); + ret = bpf_prog_run_pin_on_cpu(prog, skb); /* strparser clones the skb before handing it to a upper layer, * meaning skb_orphan has been called. We NULL sk on the way out * to ensure we don't trigger a BUG_ON() in skb/sk operations diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index ea9e73428ed9..56fac24a627a 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -380,9 +380,7 @@ static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) struct bpf_prog *prog = psock->bpf_prog; int res; - preempt_disable(); - res = BPF_PROG_RUN(prog, skb); - preempt_enable(); + res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } -- cgit v1.2.3 From 02ad05965491ca72034327d47da6cb25f3a92603 Mon Sep 17 00:00:00 2001 From: David Miller Date: Mon, 24 Feb 2020 15:01:45 +0100 Subject: bpf: Use migrate_disable/enabe() in trampoline code. Instead of preemption disable/enable to reflect the purpose. This allows PREEMPT_RT to substitute it with an actual migration disable implementation. On non RT kernels this is still mapped to preempt_disable/enable(). Signed-off-by: David S. Miller Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145643.891428873@linutronix.de --- kernel/bpf/trampoline.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 6b264a92064b..704fa787fec0 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -367,8 +367,9 @@ out: mutex_unlock(&trampoline_mutex); } -/* The logic is similar to BPF_PROG_RUN, but with explicit rcu and preempt that - * are needed for trampoline. The macro is split into +/* The logic is similar to BPF_PROG_RUN, but with an explicit + * rcu_read_lock() and migrate_disable() which are required + * for the trampoline. The macro is split into * call _bpf_prog_enter * call prog->bpf_func * call __bpf_prog_exit @@ -378,7 +379,7 @@ u64 notrace __bpf_prog_enter(void) u64 start = 0; rcu_read_lock(); - preempt_disable(); + migrate_disable(); if (static_branch_unlikely(&bpf_stats_enabled_key)) start = sched_clock(); return start; @@ -401,7 +402,7 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) stats->nsecs += sched_clock() - start; u64_stats_update_end(&stats->syncp); } - preempt_enable(); + migrate_enable(); rcu_read_unlock(); } -- cgit v1.2.3 From 085fee1a72a9fba101a4a68a2c02fa8bd2b6f913 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:48 +0100 Subject: bpf: Use recursion prevention helpers in hashtab code The required protection is that the caller cannot be migrated to a different CPU as these places take either a hash bucket lock or might trigger a kprobe inside the memory allocator. Both scenarios can lead to deadlocks. The deadlock prevention is per CPU by incrementing a per CPU variable which temporarily blocks the invocation of BPF programs from perf and kprobes. Replace the open coded preempt_disable/enable() and this_cpu_inc/dec() pairs with the new recursion prevention helpers to prepare BPF to work on PREEMPT_RT enabled kernels. On a non-RT kernel the migrate disable/enable in the helpers map to preempt_disable/enable(), i.e. no functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145644.211208533@linutronix.de --- kernel/bpf/hashtab.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431cef22d29d..ef83b012d8d8 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1333,8 +1333,7 @@ alloc: } again: - preempt_disable(); - this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); again_nocopy: dst_key = keys; @@ -1362,8 +1361,7 @@ again_nocopy: */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); goto after_loop; } @@ -1374,8 +1372,7 @@ again_nocopy: */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); kvfree(keys); kvfree(values); goto alloc; @@ -1445,8 +1442,7 @@ next_batch: } rcu_read_unlock(); - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys, key_size * bucket_cnt) || copy_to_user(uvalues + total * value_size, values, -- cgit v1.2.3 From b6e5dae15a61b0cc9219799926813baad0b58967 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:49 +0100 Subject: bpf: Replace open coded recursion prevention in sys_bpf() The required protection is that the caller cannot be migrated to a different CPU as these functions end up in places which take either a hash bucket lock or might trigger a kprobe inside the memory allocator. Both scenarios can lead to deadlocks. The deadlock prevention is per CPU by incrementing a per CPU variable which temporarily blocks the invocation of BPF programs from perf and kprobes. Replace the open coded preempt_[dis|en]able and __this_cpu_[inc|dec] pairs with the new helper functions. These functions are already prepared to make BPF work on PREEMPT_RT enabled kernels. No functional change for !RT kernels. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145644.317843926@linutronix.de --- kernel/bpf/syscall.c | 27 ++++++++------------------- 1 file changed, 8 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a91ad518c050..a79743a89815 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -171,11 +171,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, flags); } - /* must increment bpf_prog_active to avoid kprobe+bpf triggering from - * inside bpf map update or delete otherwise deadlocks are possible - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); @@ -206,8 +202,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -222,8 +217,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, if (bpf_map_is_dev_bound(map)) return bpf_map_offload_lookup_elem(map, key, value); - preempt_disable(); - this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); @@ -268,8 +262,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, rcu_read_unlock(); } - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -1136,13 +1129,11 @@ static int map_delete_elem(union bpf_attr *attr) goto out; } - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); out: kfree(key); @@ -1254,13 +1245,11 @@ int generic_map_delete_batch(struct bpf_map *map, break; } - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); if (err) break; -- cgit v1.2.3 From d01f9b198ca985b49717d8cd0b1f57806cb1319a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:50 +0100 Subject: bpf: Factor out hashtab bucket lock operations As a preparation for making the BPF locking RT friendly, factor out the hash bucket lock operations into inline functions. This allows to do the necessary RT modification in one place instead of sprinkling it all over the place. No functional change. The now unused htab argument of the lock/unlock functions will be used in the next step which adds PREEMPT_RT support. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145644.420416916@linutronix.de --- kernel/bpf/hashtab.c | 69 ++++++++++++++++++++++++++++++++++------------------ 1 file changed, 46 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index ef83b012d8d8..9a3b926e915c 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -88,6 +88,32 @@ struct htab_elem { char key[0] __aligned(8); }; +static void htab_init_buckets(struct bpf_htab *htab) +{ + unsigned i; + + for (i = 0; i < htab->n_buckets; i++) { + INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); + raw_spin_lock_init(&htab->buckets[i].lock); + } +} + +static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab, + struct bucket *b) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&b->lock, flags); + return flags; +} + +static inline void htab_unlock_bucket(const struct bpf_htab *htab, + struct bucket *b, + unsigned long flags) +{ + raw_spin_unlock_irqrestore(&b->lock, flags); +} + static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); static bool htab_is_lru(const struct bpf_htab *htab) @@ -348,8 +374,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; - int err, i; u64 cost; + int err; htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) @@ -411,10 +437,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->hashrnd = get_random_int(); - for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); - raw_spin_lock_init(&htab->buckets[i].lock); - } + htab_init_buckets(htab); if (prealloc) { err = prealloc_init(htab); @@ -622,7 +645,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) b = __select_bucket(htab, tgt_l->hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { @@ -630,7 +653,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) break; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return l == tgt_l; } @@ -896,7 +919,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, */ } - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -937,7 +960,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, } ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return ret; } @@ -975,7 +998,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, return -ENOMEM; memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -994,7 +1017,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); if (ret) bpf_lru_push_free(&htab->lru, &l_new->lru_node); @@ -1029,7 +1052,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1052,7 +1075,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return ret; } @@ -1092,7 +1115,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, return -ENOMEM; } - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1114,7 +1137,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; @@ -1152,7 +1175,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l = lookup_elem_raw(head, hash, key, key_size); @@ -1162,7 +1185,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) ret = 0; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return ret; } @@ -1184,7 +1207,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l = lookup_elem_raw(head, hash, key, key_size); @@ -1193,7 +1216,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) ret = 0; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); if (l) bpf_lru_push_free(&htab->lru, &l->lru_node); return ret; @@ -1342,7 +1365,7 @@ again_nocopy: head = &b->head; /* do not grab the lock unless need it (bucket_cnt > 0). */ if (locked) - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) @@ -1359,7 +1382,7 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); rcu_read_unlock(); bpf_enable_instrumentation(); goto after_loop; @@ -1370,7 +1393,7 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); rcu_read_unlock(); bpf_enable_instrumentation(); kvfree(keys); @@ -1423,7 +1446,7 @@ again_nocopy: dst_val += value_size; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); locked = false; while (node_to_free) { -- cgit v1.2.3 From 7f805d17f1523c7b2c0da319ddb427d6c5d94ff1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:51 +0100 Subject: bpf: Prepare hashtab locking for PREEMPT_RT PREEMPT_RT forbids certain operations like memory allocations (even with GFP_ATOMIC) from atomic contexts. This is required because even with GFP_ATOMIC the memory allocator calls into code pathes which acquire locks with long held lock sections. To ensure the deterministic behaviour these locks are regular spinlocks, which are converted to 'sleepable' spinlocks on RT. The only true atomic contexts on an RT kernel are the low level hardware handling, scheduling, low level interrupt handling, NMIs etc. None of these contexts should ever do memory allocations. As regular device interrupt handlers and soft interrupts are forced into thread context, the existing code which does spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*(); just works. In theory the BPF locks could be converted to regular spinlocks as well, but the bucket locks and percpu_freelist locks can be taken from arbitrary contexts (perf, kprobes, tracepoints) which are required to be atomic contexts even on RT. These mechanisms require preallocated maps, so there is no need to invoke memory allocations within the lock held sections. BPF maps which need dynamic allocation are only used from (forced) thread context on RT and can therefore use regular spinlocks which in turn allows to invoke memory allocations from the lock held section. To achieve this make the hash bucket lock a union of a raw and a regular spinlock and initialize and lock/unlock either the raw spinlock for preallocated maps or the regular variant for maps which require memory allocations. On a non RT kernel this distinction is neither possible nor required. spinlock maps to raw_spinlock and the extra code and conditional is optimized out by the compiler. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145644.509685912@linutronix.de --- kernel/bpf/hashtab.c | 65 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 56 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 9a3b926e915c..53d9483fee10 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -46,10 +46,43 @@ * from one of these contexts completed. sys_bpf() uses the same mechanism * by pinning the task to the current CPU and incrementing the recursion * protection accross the map operation. + * + * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain + * operations like memory allocations (even with GFP_ATOMIC) from atomic + * contexts. This is required because even with GFP_ATOMIC the memory + * allocator calls into code pathes which acquire locks with long held lock + * sections. To ensure the deterministic behaviour these locks are regular + * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only + * true atomic contexts on an RT kernel are the low level hardware + * handling, scheduling, low level interrupt handling, NMIs etc. None of + * these contexts should ever do memory allocations. + * + * As regular device interrupt handlers and soft interrupts are forced into + * thread context, the existing code which does + * spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*(); + * just works. + * + * In theory the BPF locks could be converted to regular spinlocks as well, + * but the bucket locks and percpu_freelist locks can be taken from + * arbitrary contexts (perf, kprobes, tracepoints) which are required to be + * atomic contexts even on RT. These mechanisms require preallocated maps, + * so there is no need to invoke memory allocations within the lock held + * sections. + * + * BPF maps which need dynamic allocation are only used from (forced) + * thread context on RT and can therefore use regular spinlocks which in + * turn allows to invoke memory allocations from the lock held section. + * + * On a non RT kernel this distinction is neither possible nor required. + * spinlock maps to raw_spinlock and the extra code is optimized out by the + * compiler. */ struct bucket { struct hlist_nulls_head head; - raw_spinlock_t lock; + union { + raw_spinlock_t raw_lock; + spinlock_t lock; + }; }; struct bpf_htab { @@ -88,13 +121,26 @@ struct htab_elem { char key[0] __aligned(8); }; +static inline bool htab_is_prealloc(const struct bpf_htab *htab) +{ + return !(htab->map.map_flags & BPF_F_NO_PREALLOC); +} + +static inline bool htab_use_raw_lock(const struct bpf_htab *htab) +{ + return (!IS_ENABLED(CONFIG_PREEMPT_RT) || htab_is_prealloc(htab)); +} + static void htab_init_buckets(struct bpf_htab *htab) { unsigned i; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); - raw_spin_lock_init(&htab->buckets[i].lock); + if (htab_use_raw_lock(htab)) + raw_spin_lock_init(&htab->buckets[i].raw_lock); + else + spin_lock_init(&htab->buckets[i].lock); } } @@ -103,7 +149,10 @@ static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab, { unsigned long flags; - raw_spin_lock_irqsave(&b->lock, flags); + if (htab_use_raw_lock(htab)) + raw_spin_lock_irqsave(&b->raw_lock, flags); + else + spin_lock_irqsave(&b->lock, flags); return flags; } @@ -111,7 +160,10 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab, struct bucket *b, unsigned long flags) { - raw_spin_unlock_irqrestore(&b->lock, flags); + if (htab_use_raw_lock(htab)) + raw_spin_unlock_irqrestore(&b->raw_lock, flags); + else + spin_unlock_irqrestore(&b->lock, flags); } static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); @@ -128,11 +180,6 @@ static bool htab_is_percpu(const struct bpf_htab *htab) htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } -static bool htab_is_prealloc(const struct bpf_htab *htab) -{ - return !(htab->map.map_flags & BPF_F_NO_PREALLOC); -} - static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { -- cgit v1.2.3 From 66150d0dde030c5ee68ccd93e4c54a73c47ebebd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 24 Feb 2020 15:01:52 +0100 Subject: bpf, lpm: Make locking RT friendly The LPM trie map cannot be used in contexts like perf, kprobes and tracing as this map type dynamically allocates memory. The memory allocation happens with a raw spinlock held which is a truly spinning lock on a PREEMPT RT enabled kernel which disables preemption and interrupts. As RT does not allow memory allocation from such a section for various reasons, convert the raw spinlock to a regular spinlock. On a RT enabled kernel these locks are substituted by 'sleeping' spinlocks which provide the proper protection but keep the code preemptible. On a non-RT kernel regular spinlocks map to raw spinlocks, i.e. this does not cause any functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145644.602129531@linutronix.de --- kernel/bpf/lpm_trie.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 56e6c75d354d..3b3c420bc8ed 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -34,7 +34,7 @@ struct lpm_trie { size_t n_entries; size_t max_prefixlen; size_t data_size; - raw_spinlock_t lock; + spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to @@ -315,7 +315,7 @@ static int trie_update_elem(struct bpf_map *map, if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - raw_spin_lock_irqsave(&trie->lock, irq_flags); + spin_lock_irqsave(&trie->lock, irq_flags); /* Allocate and fill a new node */ @@ -422,7 +422,7 @@ out: kfree(im_node); } - raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } @@ -442,7 +442,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - raw_spin_lock_irqsave(&trie->lock, irq_flags); + spin_lock_irqsave(&trie->lock, irq_flags); /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node @@ -518,7 +518,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) kfree_rcu(node, rcu); out: - raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } @@ -575,7 +575,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) if (ret) goto out_err; - raw_spin_lock_init(&trie->lock); + spin_lock_init(&trie->lock); return &trie->map; out_err: -- cgit v1.2.3 From 099bfaa731ec347d3f16a463ae53b88a1700c0af Mon Sep 17 00:00:00 2001 From: David Miller Date: Mon, 24 Feb 2020 15:01:53 +0100 Subject: bpf/stackmap: Dont trylock mmap_sem with PREEMPT_RT and interrupts disabled In a RT kernel down_read_trylock() cannot be used from NMI context and up_read_non_owner() is another problematic issue. So in such a configuration, simply elide the annotated stackmap and just report the raw IPs. In the longer term, it might be possible to provide a atomic friendly versions of the page cache traversal which will at least provide the info if the pages are resident and don't need to be paged in. [ tglx: Use IS_ENABLED() to avoid the #ifdeffery, fixup the irq work callback and add a comment ] Signed-off-by: David S. Miller Signed-off-by: Thomas Gleixner Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200224145644.708960317@linutronix.de --- kernel/bpf/stackmap.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 3f958b90d914..db76339fe358 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -40,6 +40,9 @@ static void do_up_read(struct irq_work *entry) { struct stack_map_irq_work *work; + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + work = container_of(entry, struct stack_map_irq_work, irq_work); up_read_non_owner(work->sem); work->sem = NULL; @@ -288,10 +291,19 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, struct stack_map_irq_work *work = NULL; if (irqs_disabled()) { - work = this_cpu_ptr(&up_read_work); - if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) - /* cannot queue more up_read, fallback */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + work = this_cpu_ptr(&up_read_work); + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) { + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } + } else { + /* + * PREEMPT_RT does not allow to trylock mmap sem in + * interrupt disabled context. Force the fallback code. + */ irq_work_busy = true; + } } /* -- cgit v1.2.3 From d7f10df86202273155a9d8f8553bc2ad28e0dd46 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 26 Feb 2020 18:17:44 -0600 Subject: bpf: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200227001744.GA3317@embeddedor --- include/linux/bpf-cgroup.h | 2 +- include/linux/bpf.h | 2 +- include/uapi/linux/bpf.h | 2 +- kernel/bpf/bpf_struct_ops.c | 2 +- kernel/bpf/hashtab.c | 2 +- kernel/bpf/lpm_trie.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a11d5b7dbbf3..a7cd5c7a2509 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -36,7 +36,7 @@ struct bpf_cgroup_storage_map; struct bpf_storage_buffer { struct rcu_head rcu; - char data[0]; + char data[]; }; struct bpf_cgroup_storage { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1acd5bf70350..9aa33b8f3d55 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -859,7 +859,7 @@ struct bpf_prog_array_item { struct bpf_prog_array { struct rcu_head rcu; - struct bpf_prog_array_item items[0]; + struct bpf_prog_array_item items[]; }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 906e9f2752db..8e98ced0963b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,7 +73,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[0]; /* Arbitrary size */ + __u8 data[]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 042f95534f86..c498f0fffb40 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -23,7 +23,7 @@ enum bpf_struct_ops_state { struct bpf_struct_ops_value { BPF_STRUCT_OPS_COMMON_VALUE; - char data[0] ____cacheline_aligned_in_smp; + char data[] ____cacheline_aligned_in_smp; }; struct bpf_struct_ops_map { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 53d9483fee10..d541c8486c95 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -118,7 +118,7 @@ struct htab_elem { struct bpf_lru_node lru_node; }; u32 hash; - char key[0] __aligned(8); + char key[] __aligned(8); }; static inline bool htab_is_prealloc(const struct bpf_htab *htab) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 3b3c420bc8ed..65c236cf341e 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -25,7 +25,7 @@ struct lpm_trie_node { struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; - u8 data[0]; + u8 data[]; }; struct lpm_trie { -- cgit v1.2.3 From 1ed4d92458a969e71e7914550b6f0c730c14d84e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 25 Feb 2020 15:04:21 -0800 Subject: bpf: INET_DIAG support in bpf_sk_storage This patch adds INET_DIAG support to bpf_sk_storage. 1. Although this series adds bpf_sk_storage diag capability to inet sk, bpf_sk_storage is in general applicable to all fullsock. Hence, the bpf_sk_storage logic will operate on SK_DIAG_* nlattr. The caller will pass in its specific nesting nlattr (e.g. INET_DIAG_*) as the argument. 2. The request will be like: INET_DIAG_REQ_SK_BPF_STORAGES (nla_nest) (defined in latter patch) SK_DIAG_BPF_STORAGE_REQ_MAP_FD (nla_put_u32) SK_DIAG_BPF_STORAGE_REQ_MAP_FD (nla_put_u32) ...... Considering there could have multiple bpf_sk_storages in a sk, instead of reusing INET_DIAG_INFO ("ss -i"), the user can select some specific bpf_sk_storage to dump by specifying an array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD. If no SK_DIAG_BPF_STORAGE_REQ_MAP_FD is specified (i.e. an empty INET_DIAG_REQ_SK_BPF_STORAGES), it will dump all bpf_sk_storages of a sk. 3. The reply will be like: INET_DIAG_BPF_SK_STORAGES (nla_nest) (defined in latter patch) SK_DIAG_BPF_STORAGE (nla_nest) SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) SK_DIAG_BPF_STORAGE (nla_nest) SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) ...... 4. Unlike other INET_DIAG info of a sk which is pretty static, the size required to dump the bpf_sk_storage(s) of a sk is dynamic as the system adding more bpf_sk_storage_map. It is hard to set a static min_dump_alloc size. Hence, this series learns it at the runtime and adjust the cb->min_dump_alloc as it iterates all sk(s) of a system. The "unsigned int *res_diag_size" in bpf_sk_storage_diag_put() is for this purpose. The next patch will update the cb->min_dump_alloc as it iterates the sk(s). Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200225230421.1975729-1-kafai@fb.com --- include/linux/bpf.h | 1 + include/net/bpf_sk_storage.h | 27 ++++ include/uapi/linux/sock_diag.h | 26 ++++ kernel/bpf/syscall.c | 15 +++ net/core/bpf_sk_storage.c | 283 ++++++++++++++++++++++++++++++++++++++++- 5 files changed, 346 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9aa33b8f3d55..6015a4daf118 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1023,6 +1023,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); +struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 8e4f831d2e52..5036c94c0503 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -10,14 +10,41 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +struct bpf_sk_storage_diag; +struct sk_buff; +struct nlattr; +struct sock; + #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); +struct bpf_sk_storage_diag * +bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs); +void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag); +int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, + struct sock *sk, struct sk_buff *skb, + int stg_array_type, + unsigned int *res_diag_size); #else static inline int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { return 0; } +static inline struct bpf_sk_storage_diag * +bpf_sk_storage_diag_alloc(const struct nlattr *nla) +{ + return NULL; +} +static inline void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) +{ +} +static inline int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, + struct sock *sk, struct sk_buff *skb, + int stg_array_type, + unsigned int *res_diag_size) +{ + return 0; +} #endif #endif /* _BPF_SK_STORAGE_H */ diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h index e5925009a652..5f74a5f6091d 100644 --- a/include/uapi/linux/sock_diag.h +++ b/include/uapi/linux/sock_diag.h @@ -36,4 +36,30 @@ enum sknetlink_groups { }; #define SKNLGRP_MAX (__SKNLGRP_MAX - 1) +enum { + SK_DIAG_BPF_STORAGE_REQ_NONE, + SK_DIAG_BPF_STORAGE_REQ_MAP_FD, + __SK_DIAG_BPF_STORAGE_REQ_MAX, +}; + +#define SK_DIAG_BPF_STORAGE_REQ_MAX (__SK_DIAG_BPF_STORAGE_REQ_MAX - 1) + +enum { + SK_DIAG_BPF_STORAGE_REP_NONE, + SK_DIAG_BPF_STORAGE, + __SK_DIAG_BPF_STORAGE_REP_MAX, +}; + +#define SK_DIAB_BPF_STORAGE_REP_MAX (__SK_DIAG_BPF_STORAGE_REP_MAX - 1) + +enum { + SK_DIAG_BPF_STORAGE_NONE, + SK_DIAG_BPF_STORAGE_PAD, + SK_DIAG_BPF_STORAGE_MAP_ID, + SK_DIAG_BPF_STORAGE_MAP_VALUE, + __SK_DIAG_BPF_STORAGE_MAX, +}; + +#define SK_DIAG_BPF_STORAGE_MAX (__SK_DIAG_BPF_STORAGE_MAX - 1) + #endif /* _UAPI__SOCK_DIAG_H__ */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a79743a89815..c536c65256ad 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -902,6 +902,21 @@ void bpf_map_inc_with_uref(struct bpf_map *map) } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); +struct bpf_map *bpf_map_get(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_map *map; + + map = __bpf_map_get(f); + if (IS_ERR(map)) + return map; + + bpf_map_inc(map); + fdput(f); + + return map; +} + struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 3ab23f698221..3415a4896c59 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -8,6 +8,7 @@ #include #include #include +#include #include static atomic_t cache_idx; @@ -606,6 +607,14 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) kfree(map); } +/* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ +#define MAX_VALUE_SIZE \ + min_t(u32, \ + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_sk_storage_elem))) + static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || @@ -619,12 +628,7 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (attr->value_size >= KMALLOC_MAX_SIZE - - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem) || - /* U16_MAX is much more than enough for sk local storage - * considering a tcp_sock is ~2k. - */ - attr->value_size > U16_MAX - sizeof(struct bpf_sk_storage_elem)) + if (attr->value_size > MAX_VALUE_SIZE) return -E2BIG; return 0; @@ -910,3 +914,270 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_SOCKET, }; + +struct bpf_sk_storage_diag { + u32 nr_maps; + struct bpf_map *maps[]; +}; + +/* The reply will be like: + * INET_DIAG_BPF_SK_STORAGES (nla_nest) + * SK_DIAG_BPF_STORAGE (nla_nest) + * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) + * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) + * SK_DIAG_BPF_STORAGE (nla_nest) + * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) + * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) + * .... + */ +static int nla_value_size(u32 value_size) +{ + /* SK_DIAG_BPF_STORAGE (nla_nest) + * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) + * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) + */ + return nla_total_size(0) + nla_total_size(sizeof(u32)) + + nla_total_size_64bit(value_size); +} + +void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) +{ + u32 i; + + if (!diag) + return; + + for (i = 0; i < diag->nr_maps; i++) + bpf_map_put(diag->maps[i]); + + kfree(diag); +} +EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free); + +static bool diag_check_dup(const struct bpf_sk_storage_diag *diag, + const struct bpf_map *map) +{ + u32 i; + + for (i = 0; i < diag->nr_maps; i++) { + if (diag->maps[i] == map) + return true; + } + + return false; +} + +struct bpf_sk_storage_diag * +bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) +{ + struct bpf_sk_storage_diag *diag; + struct nlattr *nla; + u32 nr_maps = 0; + int rem, err; + + /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as + * the map_alloc_check() side also does. + */ + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + nla_for_each_nested(nla, nla_stgs, rem) { + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + nr_maps++; + } + + diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * nr_maps, + GFP_KERNEL); + if (!diag) + return ERR_PTR(-ENOMEM); + + nla_for_each_nested(nla, nla_stgs, rem) { + struct bpf_map *map; + int map_fd; + + if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + continue; + + map_fd = nla_get_u32(nla); + map = bpf_map_get(map_fd); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto err_free; + } + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) { + bpf_map_put(map); + err = -EINVAL; + goto err_free; + } + if (diag_check_dup(diag, map)) { + bpf_map_put(map); + err = -EEXIST; + goto err_free; + } + diag->maps[diag->nr_maps++] = map; + } + + return diag; + +err_free: + bpf_sk_storage_diag_free(diag); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); + +static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb) +{ + struct nlattr *nla_stg, *nla_value; + struct bpf_sk_storage_map *smap; + + /* It cannot exceed max nlattr's payload */ + BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE); + + nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); + if (!nla_stg) + return -EMSGSIZE; + + smap = rcu_dereference(sdata->smap); + if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) + goto errout; + + nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE, + smap->map.value_size, + SK_DIAG_BPF_STORAGE_PAD); + if (!nla_value) + goto errout; + + if (map_value_has_spin_lock(&smap->map)) + copy_map_value_locked(&smap->map, nla_data(nla_value), + sdata->data, true); + else + copy_map_value(&smap->map, nla_data(nla_value), sdata->data); + + nla_nest_end(skb, nla_stg); + return 0; + +errout: + nla_nest_cancel(skb, nla_stg); + return -EMSGSIZE; +} + +static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, + int stg_array_type, + unsigned int *res_diag_size) +{ + /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ + unsigned int diag_size = nla_total_size(0); + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage_map *smap; + struct nlattr *nla_stgs; + unsigned int saved_len; + int err = 0; + + rcu_read_lock(); + + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + rcu_read_unlock(); + return 0; + } + + nla_stgs = nla_nest_start(skb, stg_array_type); + if (!nla_stgs) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + + saved_len = skb->len; + hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { + smap = rcu_dereference(SDATA(selem)->smap); + diag_size += nla_value_size(smap->map.value_size); + + if (nla_stgs && diag_get(SDATA(selem), skb)) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + } + + rcu_read_unlock(); + + if (nla_stgs) { + if (saved_len == skb->len) + nla_nest_cancel(skb, nla_stgs); + else + nla_nest_end(skb, nla_stgs); + } + + if (diag_size == nla_total_size(0)) { + *res_diag_size = 0; + return 0; + } + + *res_diag_size = diag_size; + return err; +} + +int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, + struct sock *sk, struct sk_buff *skb, + int stg_array_type, + unsigned int *res_diag_size) +{ + /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ + unsigned int diag_size = nla_total_size(0); + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_data *sdata; + struct nlattr *nla_stgs; + unsigned int saved_len; + int err = 0; + u32 i; + + *res_diag_size = 0; + + /* No map has been specified. Dump all. */ + if (!diag->nr_maps) + return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type, + res_diag_size); + + rcu_read_lock(); + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + rcu_read_unlock(); + return 0; + } + + nla_stgs = nla_nest_start(skb, stg_array_type); + if (!nla_stgs) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + + saved_len = skb->len; + for (i = 0; i < diag->nr_maps; i++) { + sdata = __sk_storage_lookup(sk_storage, + (struct bpf_sk_storage_map *)diag->maps[i], + false); + + if (!sdata) + continue; + + diag_size += nla_value_size(diag->maps[i]->value_size); + + if (nla_stgs && diag_get(sdata, skb)) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + } + rcu_read_unlock(); + + if (nla_stgs) { + if (saved_len == skb->len) + nla_nest_cancel(skb, nla_stgs); + else + nla_nest_end(skb, nla_stgs); + } + + if (diag_size == nla_total_size(0)) { + *res_diag_size = 0; + return 0; + } + + *res_diag_size = diag_size; + return err; +} +EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); -- cgit v1.2.3