From 5c0930ccaad5a74d74e8b18b648c5eb21ed2fe94 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Nov 2023 15:57:13 +0100 Subject: hrtimers: Push pending hrtimers away from outgoing CPU earlier 2b8272ff4a70 ("cpu/hotplug: Prevent self deadlock on CPU hot-unplug") solved the straight forward CPU hotplug deadlock vs. the scheduler bandwidth timer. Yu discovered a more involved variant where a task which has a bandwidth timer started on the outgoing CPU holds a lock and then gets throttled. If the lock required by one of the CPU hotplug callbacks the hotplug operation deadlocks because the unthrottling timer event is not handled on the dying CPU and can only be recovered once the control CPU reaches the hotplug state which pulls the pending hrtimers from the dead CPU. Solve this by pushing the hrtimers away from the dying CPU in the dying callbacks. Nothing can queue a hrtimer on the dying CPU at that point because all other CPUs spin in stop_machine() with interrupts disabled and once the operation is finished the CPU is marked offline. Reported-by: Yu Liao Signed-off-by: Thomas Gleixner Tested-by: Liu Tie Link: https://lore.kernel.org/r/87a5rphara.ffs@tglx --- include/linux/cpuhotplug.h | 1 + include/linux/hrtimer.h | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068f7738be22..448f5f995adc 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -193,6 +193,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, + CPUHP_AP_HRTIMERS_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 0ee140176f10..f2044d5a652b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -531,9 +531,9 @@ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU -int hrtimers_dead_cpu(unsigned int cpu); +int hrtimers_cpu_dying(unsigned int cpu); #else -#define hrtimers_dead_cpu NULL +#define hrtimers_cpu_dying NULL #endif #endif -- cgit v1.2.3 From 889c58b3155ff4c8e8671c95daef63d6fabbb6b1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 9 Jun 2023 12:34:46 +0200 Subject: perf/core: Fix cpuctx refcounting Audit of the refcounting turned up that perf_pmu_migrate_context() fails to migrate the ctx refcount. Fixes: bd2756811766 ("perf: Rewrite core context handling") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20230612093539.085862001@infradead.org Cc: --- include/linux/perf_event.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index afb028c54f33..5547ba68e6e4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -843,11 +843,11 @@ struct perf_event { }; /* - * ,-----------------------[1:n]----------------------. - * V V - * perf_event_context <-[1:n]-> perf_event_pmu_context <--- perf_event - * ^ ^ | | - * `--------[1:n]---------' `-[n:1]-> pmu <-[1:n]-' + * ,-----------------------[1:n]------------------------. + * V V + * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event + * | | + * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed @@ -865,6 +865,9 @@ struct perf_event { * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. + * + * perf_event holds a refcount on perf_event_context + * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; -- cgit v1.2.3 From 3798680f2fbbe0ca3ab6138b34e0d161c36497ee Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 16 Nov 2023 13:12:58 +0000 Subject: rxrpc: Fix RTT determination to use any ACK as a source Fix RTT determination to be able to use any type of ACK as the response from which RTT can be calculated provided its ack.serial is non-zero and matches the serial number of an outgoing DATA or ACK packet. This shouldn't be limited to REQUESTED-type ACKs as these can have other types substituted for them for things like duplicate or out-of-order packets. Fixes: 4700c4d80b7b ("rxrpc: Fix loss of RTT samples due to interposed ACK") Signed-off-by: David Howells cc: Marc Dionne cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4c53a5ef6257..f7e537f64db4 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -328,7 +328,7 @@ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ - EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_other_ack, "OACK") \ EM(rxrpc_rtt_rx_obsolete, "OBSL") \ EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ -- cgit v1.2.3 From 9e0be3f50c0e8517d0238b62409c20bcb8cd8785 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 10 Nov 2023 13:07:22 +0100 Subject: linux/export: clean up the IA-64 KSYM_FUNC macro With commit cf8e8658100d ("arch: Remove Itanium (IA-64) architecture"), there is no need to keep the IA-64 definition of the KSYM_FUNC macro. Clean up the IA-64 definition of the KSYM_FUNC macro. Signed-off-by: Lukas Bulwahn Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- include/linux/export-internal.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index 45fca09b2319..69501e0ec239 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -50,9 +50,7 @@ " .previous" "\n" \ ) -#ifdef CONFIG_IA64 -#define KSYM_FUNC(name) @fptr(name) -#elif defined(CONFIG_PARISC) && defined(CONFIG_64BIT) +#if defined(CONFIG_PARISC) && defined(CONFIG_64BIT) #define KSYM_FUNC(name) P%name #else #define KSYM_FUNC(name) name -- cgit v1.2.3 From 79e0c5be8c73a674c92bd4ba77b75f4f8c91d32e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Nov 2023 01:42:13 +0100 Subject: net, vrf: Move dstats structure to core Just move struct pcpu_dstats out of the vrf into the core, and streamline the field names slightly, so they better align with the {t,l}stats ones. No functional change otherwise. A conversion of the u64s to u64_stats_t could be done at a separate point in future. This move is needed as we are moving the {t,l,d}stats allocation/freeing to the core. Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov Cc: Jakub Kicinski Cc: David Ahern Link: https://lore.kernel.org/r/20231114004220.6495-2-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a16c9cc063fe..98082113156e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2755,6 +2755,16 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); +struct pcpu_dstats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_drops; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; + struct u64_stats_sync syncp; +} __aligned(8 * sizeof(u64)); + struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; -- cgit v1.2.3 From 34d21de99cea9cb17967874313e5b0262527833c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Nov 2023 01:42:14 +0100 Subject: net: Move {l,t,d}stats allocation to core and convert veth & vrf Move {l,t,d}stats allocation to the core and let netdevs pick the stats type they need. That way the driver doesn't have to bother with error handling (allocation failure checking, making sure free happens in the right spot, etc) - all happening in the core. Co-developed-by: Jakub Kicinski Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann Reviewed-by: Nikolay Aleksandrov Cc: David Ahern Link: https://lore.kernel.org/r/20231114004220.6495-3-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- include/linux/netdevice.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 98082113156e..2564e209465e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1797,6 +1797,13 @@ enum netdev_ml_priv_type { ML_PRIV_CAN, }; +enum netdev_stat_type { + NETDEV_PCPU_STAT_NONE, + NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ + NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ + NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ +}; + /** * struct net_device - The DEVICE structure. * @@ -1991,10 +1998,14 @@ enum netdev_ml_priv_type { * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type - * @lstats: Loopback statistics - * @tstats: Tunnel statistics - * @dstats: Dummy statistics - * @vstats: Virtual ethernet statistics + * + * @pcpu_stat_type: Type of device statistics which the core should + * allocate/free: none, lstats, tstats, dstats. none + * means the driver is handling statistics allocation/ + * freeing internally. + * @lstats: Loopback statistics: packets, bytes + * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes + * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP @@ -2354,6 +2365,7 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; + enum netdev_stat_type pcpu_stat_type:8; union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; -- cgit v1.2.3 From 2c225425704078282e152ba692649237f78b3d7a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Nov 2023 01:42:18 +0100 Subject: bpf, netkit: Add indirect call wrapper for fetching peer dev ndo_get_peer_dev is used in tcx BPF fast path, therefore make use of indirect call wrapper and therefore optimize the bpf_redirect_peer() internal handling a bit. Add a small skb_get_peer_dev() wrapper which utilizes the INDIRECT_CALL_1() macro instead of open coding. Future work could potentially add a peer pointer directly into struct net_device in future and convert veth and netkit over to use it so that eventually ndo_get_peer_dev can be removed. Co-developed-by: Nikolay Aleksandrov Signed-off-by: Nikolay Aleksandrov Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20231114004220.6495-7-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- include/net/netkit.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/netkit.h b/include/net/netkit.h index 0ba2e6b847ca..9ec0163739f4 100644 --- a/include/net/netkit.h +++ b/include/net/netkit.h @@ -10,6 +10,7 @@ int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev)); #else static inline int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -34,5 +35,10 @@ static inline int netkit_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline struct net_device *netkit_peer_dev(struct net_device *dev) +{ + return NULL; +} #endif /* CONFIG_NETKIT */ #endif /* __NET_NETKIT_H */ -- cgit v1.2.3 From ab5cfac139ab8576fb54630d4cca23c3e690ee90 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 21 Nov 2023 04:06:56 +0200 Subject: bpf: verify callbacks as if they are called unknown number of times Prior to this patch callbacks were handled as regular function calls, execution of callback body was modeled exactly once. This patch updates callbacks handling logic as follows: - introduces a function push_callback_call() that schedules callback body verification in env->head stack; - updates prepare_func_exit() to reschedule callback body verification upon BPF_EXIT; - as calls to bpf_*_iter_next(), calls to callback invoking functions are marked as checkpoints; - is_state_visited() is updated to stop callback based iteration when some identical parent state is found. Paths with callback function invoked zero times are now verified first, which leads to necessity to modify some selftests: - the following negative tests required adding release/unlock/drop calls to avoid previously masked unrelated error reports: - cb_refs.c:underflow_prog - exceptions_fail.c:reject_rbtree_add_throw - exceptions_fail.c:reject_with_cp_reference - the following precision tracking selftests needed change in expected log trace: - verifier_subprog_precision.c:callback_result_precise (note: r0 precision is no longer propagated inside callback and I think this is a correct behavior) - verifier_subprog_precision.c:parent_callee_saved_reg_precise_with_callback - verifier_subprog_precision.c:parent_stack_slot_precise_with_callback Reported-by: Andrew Werner Closes: https://lore.kernel.org/bpf/CA+vRuzPChFNXmouzGG+wsy=6eMcfr1mFG0F3g7rbg-sedGKW3w@mail.gmail.com/ Acked-by: Andrii Nakryiko Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20231121020701.26440-7-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 24213a99cc79..dd326936dd6f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -400,6 +400,7 @@ struct bpf_verifier_state { struct bpf_idx_pair *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; + u32 callback_unroll_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ @@ -511,6 +512,10 @@ struct bpf_insn_aux_data { * this instruction, regardless of any heuristics */ bool force_checkpoint; + /* true if instruction is a call to a helper function that + * accepts callback function as a parameter. + */ + bool calls_callback; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ -- cgit v1.2.3 From bb124da69c47dd98d69361ec13244ece50bec63e Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 21 Nov 2023 04:07:00 +0200 Subject: bpf: keep track of max number of bpf_loop callback iterations In some cases verifier can't infer convergence of the bpf_loop() iteration. E.g. for the following program: static int cb(__u32 idx, struct num_context* ctx) { ctx->i++; return 0; } SEC("?raw_tp") int prog(void *_) { struct num_context ctx = { .i = 0 }; __u8 choice_arr[2] = { 0, 1 }; bpf_loop(2, cb, &ctx, 0); return choice_arr[ctx.i]; } Each 'cb' simulation would eventually return to 'prog' and reach 'return choice_arr[ctx.i]' statement. At which point ctx.i would be marked precise, thus forcing verifier to track multitude of separate states with {.i=0}, {.i=1}, ... at bpf_loop() callback entry. This commit allows "brute force" handling for such cases by limiting number of callback body simulations using 'umax' value of the first bpf_loop() parameter. For this, extend bpf_func_state with 'callback_depth' field. Increment this field when callback visiting state is pushed to states traversal stack. For frame #N it's 'callback_depth' field counts how many times callback with frame depth N+1 had been executed. Use bpf_func_state specifically to allow independent tracking of callback depths when multiple nested bpf_loop() calls are present. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20231121020701.26440-11-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index dd326936dd6f..aa4d19d0bc94 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -301,6 +301,17 @@ struct bpf_func_state { struct tnum callback_ret_range; bool in_async_callback_fn; bool in_exception_callback_fn; + /* For callback calling functions that limit number of possible + * callback executions (e.g. bpf_loop) keeps track of current + * simulated iteration number. + * Value in frame N refers to number of times callback with frame + * N+1 was simulated, e.g. for the following call: + * + * bpf_loop(..., fn, ...); | suppose current frame is N + * | fn would be simulated in frame N+1 + * | number of simulations is tracked in frame N + */ + u32 callback_depth; /* The following fields should be last. See copy_func_state() */ int acquired_refs; -- cgit v1.2.3 From 125b0bb95dd6bec81b806b997a4ccb026eeecf8f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 9 Nov 2023 22:22:13 -0800 Subject: asm-generic: qspinlock: fix queued_spin_value_unlocked() implementation We really don't want to do atomic_read() or anything like that, since we already have the value, not the lock. The whole point of this is that we've loaded the lock from memory, and we want to check whether the value we loaded was a locked one or not. The main use of this is the lockref code, which loads both the lock and the reference count in one atomic operation, and then works on that combined value. With the atomic_read(), the compiler would pointlessly spill the value to the stack, in order to then be able to read it back "atomically". This is the qspinlock version of commit c6f4a9002252 ("asm-generic: ticket-lock: Optimize arch_spin_value_unlocked()") which fixed this same bug for ticket locks. Cc: Guo Ren Cc: Ingo Molnar Cc: Waiman Long Link: https://lore.kernel.org/all/CAHk-=whNRv0v6kQiV5QO6DJhjH4KEL36vWQ6Re8Csrnh4zbRkQ@mail.gmail.com/ Signed-off-by: Linus Torvalds --- include/asm-generic/qspinlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 995513fa2690..0655aa5b57b2 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -70,7 +70,7 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { - return !atomic_read(&lock.val); + return !lock.val.counter; } /** -- cgit v1.2.3