From 1a365e822372ba24c9da0822bc583894f6f3d821 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 20 Nov 2019 16:57:15 +0100 Subject: locking/spinlock/debug: Fix various data races This fixes various data races in spinlock_debug. By testing with KCSAN, it is observable that the console gets spammed with data races reports, suggesting these are extremely frequent. Example data race report: read to 0xffff8ab24f403c48 of 4 bytes by task 221 on cpu 2: debug_spin_lock_before kernel/locking/spinlock_debug.c:85 [inline] do_raw_spin_lock+0x9b/0x210 kernel/locking/spinlock_debug.c:112 __raw_spin_lock include/linux/spinlock_api_smp.h:143 [inline] _raw_spin_lock+0x39/0x40 kernel/locking/spinlock.c:151 spin_lock include/linux/spinlock.h:338 [inline] get_partial_node.isra.0.part.0+0x32/0x2f0 mm/slub.c:1873 get_partial_node mm/slub.c:1870 [inline] write to 0xffff8ab24f403c48 of 4 bytes by task 167 on cpu 3: debug_spin_unlock kernel/locking/spinlock_debug.c:103 [inline] do_raw_spin_unlock+0xc9/0x1a0 kernel/locking/spinlock_debug.c:138 __raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:159 [inline] _raw_spin_unlock_irqrestore+0x2d/0x50 kernel/locking/spinlock.c:191 spin_unlock_irqrestore include/linux/spinlock.h:393 [inline] free_debug_processing+0x1b3/0x210 mm/slub.c:1214 __slab_free+0x292/0x400 mm/slub.c:2864 As a side-effect, with KCSAN, this eventually locks up the console, most likely due to deadlock, e.g. .. -> printk lock -> spinlock_debug -> KCSAN detects data race -> kcsan_print_report() -> printk lock -> deadlock. This fix will 1) avoid the data races, and 2) allow using lock debugging together with KCSAN. Reported-by: Qian Cai Signed-off-by: Marco Elver Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: https://lkml.kernel.org/r/20191120155715.28089-1-elver@google.com Signed-off-by: Ingo Molnar --- kernel/locking/spinlock_debug.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 399669f7eba8..472dd462a40c 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init); static void spin_dump(raw_spinlock_t *lock, const char *msg) { - struct task_struct *owner = NULL; + struct task_struct *owner = READ_ONCE(lock->owner); - if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT) - owner = lock->owner; + if (owner == SPINLOCK_OWNER_INIT) + owner = NULL; printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n", msg, raw_smp_processor_id(), current->comm, task_pid_nr(current)); printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, " ".owner_cpu: %d\n", - lock, lock->magic, + lock, READ_ONCE(lock->magic), owner ? owner->comm : "", owner ? task_pid_nr(owner) : -1, - lock->owner_cpu); + READ_ONCE(lock->owner_cpu)); dump_stack(); } @@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg) static inline void debug_spin_lock_before(raw_spinlock_t *lock) { - SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); - SPIN_BUG_ON(lock->owner == current, lock, "recursion"); - SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion"); + SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(), lock, "cpu recursion"); } static inline void debug_spin_lock_after(raw_spinlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_spin_unlock(raw_spinlock_t *lock) @@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock) SPIN_BUG_ON(lock->owner != current, lock, "wrong owner"); SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } /* @@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock) static inline void debug_write_lock_after(rwlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_write_unlock(rwlock_t *lock) @@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock) RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner"); RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } void do_raw_write_lock(rwlock_t *lock) -- cgit From 0b8d616fb5a8ffa307b1d3af37f55c15dae14f28 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 9 Oct 2019 13:48:09 +0200 Subject: taskstats: fix data-race When assiging and testing taskstats in taskstats_exit() there's a race when setting up and reading sig->stats when a thread-group with more than one thread exits: write to 0xffff8881157bbe10 of 8 bytes by task 7951 on cpu 0: taskstats_tgid_alloc kernel/taskstats.c:567 [inline] taskstats_exit+0x6b7/0x717 kernel/taskstats.c:596 do_exit+0x2c2/0x18e0 kernel/exit.c:864 do_group_exit+0xb4/0x1c0 kernel/exit.c:983 get_signal+0x2a2/0x1320 kernel/signal.c:2734 do_signal+0x3b/0xc00 arch/x86/kernel/signal.c:815 exit_to_usermode_loop+0x250/0x2c0 arch/x86/entry/common.c:159 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline] syscall_return_slowpath arch/x86/entry/common.c:274 [inline] do_syscall_64+0x2d7/0x2f0 arch/x86/entry/common.c:299 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffff8881157bbe10 of 8 bytes by task 7949 on cpu 1: taskstats_tgid_alloc kernel/taskstats.c:559 [inline] taskstats_exit+0xb2/0x717 kernel/taskstats.c:596 do_exit+0x2c2/0x18e0 kernel/exit.c:864 do_group_exit+0xb4/0x1c0 kernel/exit.c:983 __do_sys_exit_group kernel/exit.c:994 [inline] __se_sys_exit_group kernel/exit.c:992 [inline] __x64_sys_exit_group+0x2e/0x30 kernel/exit.c:992 do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fix this by using smp_load_acquire() and smp_store_release(). Reported-by: syzbot+c5d03165a1bd1dead0c1@syzkaller.appspotmail.com Fixes: 34ec12349c8a ("taskstats: cleanup ->signal->stats allocation") Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner Acked-by: Marco Elver Reviewed-by: Will Deacon Reviewed-by: Andrea Parri Reviewed-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20191009114809.8643-1-christian.brauner@ubuntu.com --- kernel/taskstats.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 13a0f2e6ebc2..e2ac0e37c4ae 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct taskstats *stats; + struct taskstats *stats_new, *stats; - if (sig->stats || thread_group_empty(tsk)) - goto ret; + /* Pairs with smp_store_release() below. */ + stats = smp_load_acquire(&sig->stats); + if (stats || thread_group_empty(tsk)) + return stats; /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); - if (!sig->stats) { - sig->stats = stats; - stats = NULL; + stats = sig->stats; + if (!stats) { + /* + * Pairs with smp_store_release() above and order the + * kmem_cache_zalloc(). + */ + smp_store_release(&sig->stats, stats_new); + stats = stats_new; + stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); - if (stats) - kmem_cache_free(taskstats_cache, stats); -ret: - return sig->stats; + if (stats_new) + kmem_cache_free(taskstats_cache, stats_new); + + return stats; } /* Send pid data out on exit */ -- cgit From c571b72e2b845ca0519670cb7c4b5fe5f56498a5 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 10 Dec 2019 14:05:23 -0800 Subject: Revert "locking/mutex: Complain upon mutex API misuse in IRQ contexts" This ended up causing some noise in places such as rxrpc running in softirq. The warning is misleading in this case as the mutex trylock and unlock operations are done within the same context; and therefore we need not worry about the PI-boosting issues that comes along with no single-owner lock guarantees. While we don't want to support this in mutexes, there is no way out of this yet; so lets get rid of the WARNs for now, as it is only fair to code that has historically relied on non-preemptible softirq guarantees. In addition, changing the lock type is also unviable: exclusive rwsems have the same issue (just not the WARN_ON) and counting semaphores would introduce a performance hit as mutexes are a lot more optimized. This reverts: a0855d24fc22: ("locking/mutex: Complain upon mutex API misuse in IRQ contexts") Fixes: a0855d24fc22: ("locking/mutex: Complain upon mutex API misuse in IRQ contexts") Signed-off-by: Davidlohr Bueso Tested-by: David Howells Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-afs@lists.infradead.org Cc: linux-fsdevel@vger.kernel.org Cc: will@kernel.org Link: https://lkml.kernel.org/r/20191210220523.28540-1-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 54cc5f9286e9..5352ce50a97e 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -733,9 +733,6 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne */ void __sched mutex_unlock(struct mutex *lock) { -#ifdef CONFIG_DEBUG_MUTEXES - WARN_ON(in_interrupt()); -#endif #ifndef CONFIG_DEBUG_LOCK_ALLOC if (__mutex_unlock_fast(lock)) return; @@ -1416,7 +1413,6 @@ int __sched mutex_trylock(struct mutex *lock) #ifdef CONFIG_DEBUG_MUTEXES DEBUG_LOCKS_WARN_ON(lock->magic != lock); - WARN_ON(in_interrupt()); #endif locked = __mutex_trylock(lock); -- cgit From 4c80c7bc583a87ded5f61906f81256b57c795806 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Dec 2019 21:35:46 +0100 Subject: bpf: Fix build in minimal configurations, again Building with -Werror showed another failure: kernel/bpf/btf.c: In function 'btf_get_prog_ctx_type.isra.31': kernel/bpf/btf.c:3508:63: error: array subscript 0 is above array bounds of 'u8[0]' {aka 'unsigned char[0]'} [-Werror=array-bounds] ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; I don't actually understand why the array is empty, but a similar fix has addressed a related problem, so I suppose we can do the same thing here. Fixes: ce27709b8162 ("bpf: Fix build in minimal configurations") Signed-off-by: Arnd Bergmann Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191210203553.2941035-1-arnd@arndb.de --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7d40da240891..ed2075884724 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3470,6 +3470,7 @@ static u8 bpf_ctx_convert_map[] = { [_id] = __ctx_convert##_id, #include #undef BPF_PROG_TYPE + 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE -- cgit From b91e014f078e2e4f24778680e28dbbdecc7f0eb9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 8 Dec 2019 16:01:13 -0800 Subject: bpf: Make BPF trampoline use register_ftrace_direct() API Make BPF trampoline attach its generated assembly code to kernel functions via register_ftrace_direct() API. It helps ftrace-based tracers co-exist with BPF trampoline on the same kernel function. It also switches attaching logic from arch specific text_poke to generic ftrace that is available on many architectures. text_poke is still necessary for bpf-to-bpf attach and for bpf_tail_call optimization. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191209000114.1876138-3-ast@kernel.org --- include/linux/bpf.h | 1 + kernel/bpf/trampoline.c | 64 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 35903f148be5..ac7de5291509 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -461,6 +461,7 @@ struct bpf_trampoline { struct { struct btf_func_model model; void *addr; + bool ftrace_managed; } func; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 7e89f1f49d77..23b0d5cfd47e 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -3,6 +3,7 @@ #include #include #include +#include /* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ #define TRAMPOLINE_HASH_BITS 10 @@ -59,6 +60,60 @@ out: return tr; } +static int is_ftrace_location(void *ip) +{ + long addr; + + addr = ftrace_location((long)ip); + if (!addr) + return 0; + if (WARN_ON_ONCE(addr != (long)ip)) + return -EFAULT; + return 1; +} + +static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = unregister_ftrace_direct((long)ip, (long)old_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + return ret; +} + +static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + return ret; +} + +/* first time registering */ +static int register_fentry(struct bpf_trampoline *tr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + ret = is_ftrace_location(ip); + if (ret < 0) + return ret; + tr->func.ftrace_managed = ret; + + if (tr->func.ftrace_managed) + ret = register_ftrace_direct((long)ip, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + return ret; +} + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 */ @@ -77,8 +132,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) int err; if (fentry_cnt + fexit_cnt == 0) { - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, NULL); + err = unregister_fentry(tr, old_image); tr->selector = 0; goto out; } @@ -105,12 +159,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (tr->selector) /* progs already running at this address */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, new_image); + err = modify_fentry(tr, old_image, new_image); else /* first time registering */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL, - new_image); + err = register_fentry(tr, new_image); if (err) goto out; tr->selector++; -- cgit From 85572c2c4a45a541e880e087b5b17a48198b2416 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 11 Dec 2019 11:28:41 +0100 Subject: cpufreq: Avoid leaving stale IRQ work items during CPU offline The scheduler code calling cpufreq_update_util() may run during CPU offline on the target CPU after the IRQ work lists have been flushed for it, so the target CPU should be prevented from running code that may queue up an IRQ work item on it at that point. Unfortunately, that may not be the case if dvfs_possible_from_any_cpu is set for at least one cpufreq policy in the system, because that allows the CPU going offline to run the utilization update callback of the cpufreq governor on behalf of another (online) CPU in some cases. If that happens, the cpufreq governor callback may queue up an IRQ work on the CPU running it, which is going offline, and the IRQ work may not be flushed after that point. Moreover, that IRQ work cannot be flushed until the "offlining" CPU goes back online, so if any other CPU calls irq_work_sync() to wait for the completion of that IRQ work, it will have to wait until the "offlining" CPU is back online and that may not happen forever. In particular, a system-wide deadlock may occur during CPU online as a result of that. The failing scenario is as follows. CPU0 is the boot CPU, so it creates a cpufreq policy and becomes the "leader" of it (policy->cpu). It cannot go offline, because it is the boot CPU. Next, other CPUs join the cpufreq policy as they go online and they leave it when they go offline. The last CPU to go offline, say CPU3, may queue up an IRQ work while running the governor callback on behalf of CPU0 after leaving the cpufreq policy because of the dvfs_possible_from_any_cpu effect described above. Then, CPU0 is the only online CPU in the system and the stale IRQ work is still queued on CPU3. When, say, CPU1 goes back online, it will run irq_work_sync() to wait for that IRQ work to complete and so it will wait for CPU3 to go back online (which may never happen even in principle), but (worse yet) CPU0 is waiting for CPU1 at that point too and a system-wide deadlock occurs. To address this problem notice that CPUs which cannot run cpufreq utilization update code for themselves (for example, because they have left the cpufreq policies that they belonged to), should also be prevented from running that code on behalf of the other CPUs that belong to a cpufreq policy with dvfs_possible_from_any_cpu set and so in that case the cpufreq_update_util_data pointer of the CPU running the code must not be NULL as well as for the CPU which is the target of the cpufreq utilization update in progress. Accordingly, change cpufreq_this_cpu_can_update() into a regular function in kernel/sched/cpufreq.c (instead of a static inline in a header file) and make it check the cpufreq_update_util_data pointer of the local CPU if dvfs_possible_from_any_cpu is set for the target cpufreq policy. Also update the schedutil governor to do the cpufreq_this_cpu_can_update() check in the non-fast-switch case too to avoid the stale IRQ work issues. Fixes: 99d14d0e16fa ("cpufreq: Process remote callbacks from any CPU if the platform permits") Link: https://lore.kernel.org/linux-pm/20191121093557.bycvdo4xyinbc5cb@vireshk-i7/ Reported-by: Anson Huang Tested-by: Anson Huang Cc: 4.14+ # 4.14+ Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Tested-by: Peng Fan (i.MX8QXP-MEK) Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 11 ----------- include/linux/sched/cpufreq.h | 3 +++ kernel/sched/cpufreq.c | 18 ++++++++++++++++++ kernel/sched/cpufreq_schedutil.c | 8 +++----- 4 files changed, 24 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 92d5fdc8154e..31b1b0e03df8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -595,17 +595,6 @@ struct governor_attr { size_t count); }; -static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) -{ - /* - * Allow remote callbacks if: - * - dvfs_possible_from_any_cpu flag is set - * - the local and remote CPUs share cpufreq policy - */ - return policy->dvfs_possible_from_any_cpu || - cpumask_test_cpu(smp_processor_id(), policy->cpus); -} - /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index afa940cd50dc..cc6bcc1e96bc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -12,6 +12,8 @@ #define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy; + struct update_util_data { void (*func)(struct update_util_data *data, u64 time, unsigned int flags); }; @@ -20,6 +22,7 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index b5dcd1d83c7f..7c2fe50fd76d 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -5,6 +5,8 @@ * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki */ +#include + #include "sched.h" DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); @@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu) rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL); } EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook); + +/** + * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated. + * @policy: cpufreq policy to check. + * + * Return 'true' if: + * - the local and remote CPUs share @policy, + * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going + * offline (in which case it is not expected to run cpufreq updates any more). + */ +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) +{ + return cpumask_test_cpu(smp_processor_id(), policy->cpus) || + (policy->dvfs_possible_from_any_cpu && + rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data))); +} diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 322ca8860f54..9b8916fd00a2 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) * by the hardware, as calculating the frequency is pointless if * we cannot in fact act on it. * - * For the slow switching platforms, the kthread is always scheduled on - * the right set of CPUs and any CPU can find the next frequency and - * schedule the kthread. + * This is needed on the slow switching platforms too to prevent CPUs + * going offline from leaving stale IRQ work items behind. */ - if (sg_policy->policy->fast_switch_enabled && - !cpufreq_this_cpu_can_update(sg_policy->policy)) + if (!cpufreq_this_cpu_can_update(sg_policy->policy)) return false; if (unlikely(sg_policy->limits_changed)) { -- cgit From a2ea07465c8d7984cc6b8b1f0b3324f9b138094a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 16 Dec 2019 17:49:00 +0100 Subject: bpf: Fix missing prog untrack in release_maps Commit da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") wrongly assumed that in case of prog load errors, we're cleaning up all program tracking via bpf_free_used_maps(). However, it can happen that we're still at the point where we didn't copy map pointers into the prog's aux section such that env->prog->aux->used_maps is still zero, running into a UAF. In such case, the verifier has similar release_maps() helper that drops references to used maps from its env. Consolidate the release code into __bpf_free_used_maps() and call it from all sides to fix it. Fixes: da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/1c2909484ca524ae9f55109b06f22b6213e76376.1576514756.git.daniel@iogearbox.net --- include/linux/bpf.h | 2 ++ kernel/bpf/core.c | 14 ++++++++++---- kernel/bpf/verifier.c | 14 ++------------ 3 files changed, 14 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ac7de5291509..085a59afba85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -818,6 +818,8 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); 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); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 49e32acad7d8..6231858df723 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2048,18 +2048,24 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) } } -static void bpf_free_used_maps(struct bpf_prog_aux *aux) +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len) { struct bpf_map *map; - int i; + u32 i; bpf_free_cgroup_storage(aux); - for (i = 0; i < aux->used_map_cnt; i++) { - map = aux->used_maps[i]; + for (i = 0; i < len; i++) { + map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); bpf_map_put(map); } +} + +static void bpf_free_used_maps(struct bpf_prog_aux *aux) +{ + __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 034ef81f935b..a1acdce77070 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8298,18 +8298,8 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { - enum bpf_cgroup_storage_type stype; - int i; - - for_each_cgroup_storage_type(stype) { - if (!env->prog->aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage[stype]); - } - - for (i = 0; i < env->used_map_cnt; i++) - bpf_map_put(env->used_maps[i]); + __bpf_free_used_maps(env->prog->aux, env->used_maps, + env->used_map_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ -- cgit From 9f0bff1180efc9ea988fed3fd93da7647151ac8b Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 19 Nov 2019 13:14:29 +0100 Subject: perf/core: Add SRCU annotation for pmus list walk Since commit 28875945ba98d ("rcu: Add support for consolidated-RCU reader checking") there is an additional check to ensure that a RCU related lock is held while the RCU list is iterated. This section holds the SRCU reader lock instead. Add annotation to list_for_each_entry_rcu() that pmus_srcu must be acquired during the list traversal. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Joel Fernandes (Google) Link: https://lkml.kernel.org/r/20191119121429.zhcubzdhm672zasg@linutronix.de --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ff86d57f9e5..a1f8bde19b56 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10523,7 +10523,7 @@ again: goto unlock; } - list_for_each_entry_rcu(pmu, &pmus, entry) { + list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) { ret = perf_try_init_event(pmu, event); if (!ret) goto unlock; -- cgit From 3dfbe25c27eab7c90c8a7e97b4c354a9d24dd985 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 3 Dec 2019 13:35:23 -0500 Subject: sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Jingfeng reports rare div0 crashes in psi on systems with some uptime: [58914.066423] divide error: 0000 [#1] SMP [58914.070416] Modules linked in: ipmi_poweroff ipmi_watchdog toa overlay fuse tcp_diag inet_diag binfmt_misc aisqos(O) aisqos_hotfixes(O) [58914.083158] CPU: 94 PID: 140364 Comm: kworker/94:2 Tainted: G W OE K 4.9.151-015.ali3000.alios7.x86_64 #1 [58914.093722] Hardware name: Alibaba Alibaba Cloud ECS/Alibaba Cloud ECS, BIOS 3.23.34 02/14/2019 [58914.102728] Workqueue: events psi_update_work [58914.107258] task: ffff8879da83c280 task.stack: ffffc90059dcc000 [58914.113336] RIP: 0010:[] [] psi_update_stats+0x1c1/0x330 [58914.122183] RSP: 0018:ffffc90059dcfd60 EFLAGS: 00010246 [58914.127650] RAX: 0000000000000000 RBX: ffff8858fe98be50 RCX: 000000007744d640 [58914.134947] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00003594f700648e [58914.142243] RBP: ffffc90059dcfdf8 R08: 0000359500000000 R09: 0000000000000000 [58914.149538] R10: 0000000000000000 R11: 0000000000000000 R12: 0000359500000000 [58914.156837] R13: 0000000000000000 R14: 0000000000000000 R15: ffff8858fe98bd78 [58914.164136] FS: 0000000000000000(0000) GS:ffff887f7f380000(0000) knlGS:0000000000000000 [58914.172529] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [58914.178467] CR2: 00007f2240452090 CR3: 0000005d5d258000 CR4: 00000000007606f0 [58914.185765] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [58914.193061] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [58914.200360] PKRU: 55555554 [58914.203221] Stack: [58914.205383] ffff8858fe98bd48 00000000000002f0 0000002e81036d09 ffffc90059dcfde8 [58914.213168] ffff8858fe98bec8 0000000000000000 0000000000000000 0000000000000000 [58914.220951] 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [58914.228734] Call Trace: [58914.231337] [] psi_update_work+0x22/0x60 [58914.237067] [] process_one_work+0x189/0x420 [58914.243063] [] worker_thread+0x4e/0x4b0 [58914.248701] [] ? process_one_work+0x420/0x420 [58914.254869] [] kthread+0xe6/0x100 [58914.259994] [] ? kthread_park+0x60/0x60 [58914.265640] [] ret_from_fork+0x39/0x50 [58914.271193] Code: 41 29 c3 4d 39 dc 4d 0f 42 dc <49> f7 f1 48 8b 13 48 89 c7 48 c1 [58914.279691] RIP [] psi_update_stats+0x1c1/0x330 The crashing instruction is trying to divide the observed stall time by the sampling period. The period, stored in R8, is not 0, but we are dividing by the lower 32 bits only, which are all 0 in this instance. We could switch to a 64-bit division, but the period shouldn't be that big in the first place. It's the time between the last update and the next scheduled one, and so should always be around 2s and comfortably fit into 32 bits. The bug is in the initialization of new cgroups: we schedule the first sampling event in a cgroup as an offset of sched_clock(), but fail to initialize the last_update timestamp, and it defaults to 0. That results in a bogusly large sampling period the first time we run the sampling code, and consequently we underreport pressure for the first 2s of a cgroup's life. But worse, if sched_clock() is sufficiently advanced on the system, and the user gets unlucky, the period's lower 32 bits can all be 0 and the sampling division will crash. Fix this by initializing the last update timestamp to the creation time of the cgroup, thus correctly marking the start of the first pressure sampling period in a new cgroup. Reported-by: Jingfeng Xie Signed-off-by: Johannes Weiner Signed-off-by: Peter Zijlstra (Intel) Cc: Suren Baghdasaryan Link: https://lkml.kernel.org/r/20191203183524.41378-2-hannes@cmpxchg.org --- kernel/sched/psi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 517e3719027e..970db4686dd4 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -185,7 +185,8 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); - group->avg_next_update = sched_clock() + psi_period; + group->avg_last_update = sched_clock(); + group->avg_next_update = group->avg_last_update + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); /* Init trigger-related members */ -- cgit From c3466952ca1514158d7c16c9cfc48c27d5c5dc0f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 3 Dec 2019 13:35:24 -0500 Subject: psi: Fix a division error in psi poll() The psi window size is a u64 an can be up to 10 seconds right now, which exceeds the lower 32 bits of the variable. We currently use div_u64 for it, which is meant only for 32-bit divisors. The result is garbage pressure sampling values and even potential div0 crashes. Use div64_u64. Signed-off-by: Johannes Weiner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Suren Baghdasaryan Cc: Jingfeng Xie Link: https://lkml.kernel.org/r/20191203183524.41378-3-hannes@cmpxchg.org --- kernel/sched/psi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 970db4686dd4..ce8f6748678a 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -482,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) u32 remaining; remaining = win->size - elapsed; - growth += div_u64(win->prev_growth * remaining, win->size); + growth += div64_u64(win->prev_growth * remaining, win->size); } return growth; -- cgit From 7ed735c33104f3c6194fbc67e3a8b6e64ae84ad1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 4 Dec 2019 19:21:40 +0100 Subject: sched/fair: Fix find_idlest_group() to handle CPU affinity Because of CPU affinity, the local group can be skipped which breaks the assumption that statistics are always collected for local group. With uninitialized local_sgs, the comparison is meaningless and the behavior unpredictable. This can even end up to use local pointer which is to NULL in this case. If the local group has been skipped because of CPU affinity, we return the idlest group. Fixes: 57abff067a08 ("sched/fair: Rework find_idlest_group()") Reported-by: John Stultz Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: John Stultz Cc: rostedt@goodmis.org Cc: valentin.schneider@arm.com Cc: mingo@redhat.com Cc: mgorman@suse.de Cc: juri.lelli@redhat.com Cc: dietmar.eggemann@arm.com Cc: bsegall@google.com Cc: qais.yousef@arm.com Link: https://lkml.kernel.org/r/1575483700-22153-1-git-send-email-vincent.guittot@linaro.org --- kernel/sched/fair.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 08a233e97a01..146b6c83633f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8417,6 +8417,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, if (!idlest) return NULL; + /* The local group has been skipped because of CPU affinity */ + if (!local) + return idlest; + /* * If the local group is idler than the selected idlest group * don't try and push the task. -- cgit From 6cf82d559e1a1d89f06ff4d428aca479c1dd0be6 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 29 Nov 2019 15:04:47 +0100 Subject: sched/cfs: fix spurious active migration The load balance can fail to find a suitable task during the periodic check because the imbalance is smaller than half of the load of the waiting tasks. This results in the increase of the number of failed load balance, which can end up to start an active migration. This active migration is useless because the current running task is not a better choice than the waiting ones. In fact, the current task was probably not running but waiting for the CPU during one of the previous attempts and it had already not been selected. When load balance fails too many times to migrate a task, we should relax the contraint on the maximum load of the tasks that can be migrated similarly to what is done with cache hotness. Before the rework, load balance used to set the imbalance to the average load_per_task in order to mitigate such situation. This increased the likelihood of migrating a task but also of selecting a larger task than needed while more appropriate ones were in the list. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1575036287-6052-1-git-send-email-vincent.guittot@linaro.org --- kernel/sched/fair.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 146b6c83633f..ba749f579714 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7328,7 +7328,14 @@ static int detach_tasks(struct lb_env *env) load < 16 && !env->sd->nr_balance_failed) goto next; - if (load/2 > env->imbalance) + /* + * Make sure that we don't migrate too much load. + * Nevertheless, let relax the constraint if + * scheduler fails to find a good waiting task to + * migrate. + */ + if (load/2 > env->imbalance && + env->sd->nr_balance_failed <= env->sd->cache_nice_tries) goto next; env->imbalance -= load; -- cgit From e47304232b373362228bf233f17bd12b11c9aafc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 17 Dec 2019 13:28:16 +0100 Subject: bpf: Fix cgroup local storage prog tracking Recently noticed that we're tracking programs related to local storage maps through their prog pointer. This is a wrong assumption since the prog pointer can still change throughout the verification process, for example, whenever bpf_patch_insn_single() is called. Therefore, the prog pointer that was assigned via bpf_cgroup_storage_assign() is not guaranteed to be the same as we pass in bpf_cgroup_storage_release() and the map would therefore remain in busy state forever. Fix this by using the prog's aux pointer which is stable throughout verification and beyond. Fixes: de9cbbaadba5 ("bpf: introduce cgroup storage maps") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Roman Gushchin Cc: Martin KaFai Lau Link: https://lore.kernel.org/bpf/1471c69eca3022218666f909bc927a92388fd09e.1576580332.git.daniel@iogearbox.net --- include/linux/bpf-cgroup.h | 8 ++++---- kernel/bpf/core.c | 3 +-- kernel/bpf/local_storage.c | 24 ++++++++++++------------ kernel/bpf/verifier.c | 2 +- 4 files changed, 18 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 169fd25f6bc2..9be71c195d74 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -157,8 +157,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, @@ -360,9 +360,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, static inline void bpf_cgroup_storage_set( struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} -static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, +static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } -static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, +static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6231858df723..af6b738cf435 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2043,8 +2043,7 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) for_each_cgroup_storage_type(stype) { if (!aux->cgroup_storage[stype]) continue; - bpf_cgroup_storage_release(aux->prog, - aux->cgroup_storage[stype]); + bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]); } } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 2ba750725cb2..6bf605dd4b94 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; - struct bpf_prog *prog; + struct bpf_prog_aux *aux; struct rb_root root; struct list_head list; }; @@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_seq_show_elem = cgroup_storage_seq_show_elem, }; -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); @@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) spin_lock_bh(&map->lock); - if (map->prog && map->prog != prog) + if (map->aux && map->aux != aux) goto unlock; - if (prog->aux->cgroup_storage[stype] && - prog->aux->cgroup_storage[stype] != _map) + if (aux->cgroup_storage[stype] && + aux->cgroup_storage[stype] != _map) goto unlock; - map->prog = prog; - prog->aux->cgroup_storage[stype] = _map; + map->aux = aux; + aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -443,16 +443,16 @@ unlock: return ret; } -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); - if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage[stype] != _map); - map->prog = NULL; - prog->aux->cgroup_storage[stype] = NULL; + if (map->aux == aux) { + WARN_ON(aux->cgroup_storage[stype] != _map); + map->aux = NULL; + aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a1acdce77070..6ef71429d997 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8268,7 +8268,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog, map)) { + bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; -- cgit From cc52d9140aa920d8d61c7f6de3fff5fea6692ea9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 19 Dec 2019 22:19:50 +0100 Subject: bpf: Fix record_func_key to perform backtracking on r3 While testing Cilium with /unreleased/ Linus' tree under BPF-based NodePort implementation, I noticed a strange BPF SNAT engine behavior from time to time. In some cases it would do the correct SNAT/DNAT service translation, but at a random point in time it would just stop and perform an unexpected translation after SYN, SYN/ACK and stack would send a RST back. While initially assuming that there is some sort of a race condition in BPF code, adding trace_printk()s for debugging purposes at some point seemed to have resolved the issue auto-magically. Digging deeper on this Heisenbug and reducing the trace_printk() calls to an absolute minimum, it turns out that a single call would suffice to trigger / not trigger the seen RST issue, even though the logic of the program itself remains unchanged. Turns out the single call changed verifier pruning behavior to get everything to work. Reconstructing a minimal test case, the incorrect JIT dump looked as follows: # bpftool p d j i 11346 0xffffffffc0cba96c: [...] 21: movzbq 0x30(%rdi),%rax 26: cmp $0xd,%rax 2a: je 0x000000000000003a 2c: xor %edx,%edx 2e: movabs $0xffff89cc74e85800,%rsi 38: jmp 0x0000000000000049 3a: mov $0x2,%edx 3f: movabs $0xffff89cc74e85800,%rsi 49: mov -0x224(%rbp),%eax 4f: cmp $0x20,%eax 52: ja 0x0000000000000062 54: add $0x1,%eax 57: mov %eax,-0x224(%rbp) 5d: jmpq 0xffffffffffff6911 62: mov $0x1,%eax [...] Hence, unexpectedly, JIT emitted a direct jump even though retpoline based one would have been needed since in line 2c and 3a we have different slot keys in BPF reg r3. Verifier log of the test case reveals what happened: 0: (b7) r0 = 14 1: (73) *(u8 *)(r1 +48) = r0 2: (71) r0 = *(u8 *)(r1 +48) 3: (15) if r0 == 0xd goto pc+4 R0_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R1=ctx(id=0,off=0,imm=0) R10=fp0 4: (b7) r3 = 0 5: (18) r2 = 0xffff89cc74d54a00 7: (05) goto pc+3 11: (85) call bpf_tail_call#12 12: (b7) r0 = 1 13: (95) exit from 3 to 8: R0_w=inv13 R1=ctx(id=0,off=0,imm=0) R10=fp0 8: (b7) r3 = 2 9: (18) r2 = 0xffff89cc74d54a00 11: safe processed 13 insns (limit 1000000) [...] Second branch is pruned by verifier since considered safe, but issue is that record_func_key() couldn't have seen the index in line 3a and therefore decided that emitting a direct jump at this location was okay. Fix this by reusing our backtracking logic for precise scalar verification in order to prevent pruning on the slot key. This means verifier will track content of r3 all the way backwards and only prune if both scalars were unknown in state equivalence check and therefore poisoned in the first place in record_func_key(). The range is [x,x] in record_func_key() case since the slot always would have to be constant immediate. Correct verification after fix: 0: (b7) r0 = 14 1: (73) *(u8 *)(r1 +48) = r0 2: (71) r0 = *(u8 *)(r1 +48) 3: (15) if r0 == 0xd goto pc+4 R0_w=invP(id=0,umax_value=255,var_off=(0x0; 0xff)) R1=ctx(id=0,off=0,imm=0) R10=fp0 4: (b7) r3 = 0 5: (18) r2 = 0x0 7: (05) goto pc+3 11: (85) call bpf_tail_call#12 12: (b7) r0 = 1 13: (95) exit from 3 to 8: R0_w=invP13 R1=ctx(id=0,off=0,imm=0) R10=fp0 8: (b7) r3 = 2 9: (18) r2 = 0x0 11: (85) call bpf_tail_call#12 12: (b7) r0 = 1 13: (95) exit processed 15 insns (limit 1000000) [...] And correct corresponding JIT dump: # bpftool p d j i 11 0xffffffffc0dc34c4: [...] 21: movzbq 0x30(%rdi),%rax 26: cmp $0xd,%rax 2a: je 0x000000000000003a 2c: xor %edx,%edx 2e: movabs $0xffff9928b4c02200,%rsi 38: jmp 0x0000000000000049 3a: mov $0x2,%edx 3f: movabs $0xffff9928b4c02200,%rsi 49: cmp $0x4,%rdx 4d: jae 0x0000000000000093 4f: and $0x3,%edx 52: mov %edx,%edx 54: cmp %edx,0x24(%rsi) 57: jbe 0x0000000000000093 59: mov -0x224(%rbp),%eax 5f: cmp $0x20,%eax 62: ja 0x0000000000000093 64: add $0x1,%eax 67: mov %eax,-0x224(%rbp) 6d: mov 0x110(%rsi,%rdx,8),%rax 75: test %rax,%rax 78: je 0x0000000000000093 7a: mov 0x30(%rax),%rax 7e: add $0x19,%rax 82: callq 0x000000000000008e 87: pause 89: lfence 8c: jmp 0x0000000000000087 8e: mov %rax,(%rsp) 92: retq 93: mov $0x1,%eax [...] Also explicitly adding explicit env->allow_ptr_leaks to fixup_bpf_calls() since backtracking is enabled under former (direct jumps as well, but use different test). In case of only tracking different map pointers as in c93552c443eb ("bpf: properly enforce index mask to prevent out-of-bounds speculation"), pruning cannot make such short-cuts, neither if there are paths with scalar and non-scalar types as r3. mark_chain_precision() is only needed after we know that register_is_const(). If it was not the case, we already poison the key on first path and non-const key in later paths are not matching the scalar range in regsafe() either. Cilium NodePort testing passes fine as well now. Note, released kernels not affected. Fixes: d2e4c1e6c294 ("bpf: Constant map key tracking for prog array pokes") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/ac43ffdeb7386c5bd688761ed266f3722bb39823.1576789878.git.daniel@iogearbox.net --- kernel/bpf/verifier.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6ef71429d997..4983940cbdca 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4134,6 +4134,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_map *map = meta->map_ptr; struct tnum range; u64 val; + int err; if (func_id != BPF_FUNC_tail_call) return 0; @@ -4150,6 +4151,10 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } + err = mark_chain_precision(env, BPF_REG_3); + if (err) + return err; + val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); @@ -9272,7 +9277,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; - if (prog->jit_requested && !expect_blinding && + if (env->allow_ptr_leaks && !expect_blinding && + prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { -- cgit From 79e65c27f09683fbb50c33acab395d0ddf5302d2 Mon Sep 17 00:00:00 2001 From: Keita Suzuki Date: Wed, 11 Dec 2019 09:12:58 +0000 Subject: tracing: Avoid memory leak in process_system_preds() When failing in the allocation of filter_item, process_system_preds() goes to fail_mem, where the allocated filter is freed. However, this leads to memory leak of filter->filter_string and filter->prog, which is allocated before and in process_preds(). This bug has been detected by kmemleak as well. Fix this by changing kfree to __free_fiter. unreferenced object 0xffff8880658007c0 (size 32): comm "bash", pid 579, jiffies 4295096372 (age 17.752s) hex dump (first 32 bytes): 63 6f 6d 6d 6f 6e 5f 70 69 64 20 20 3e 20 31 30 common_pid > 10 00 00 00 00 00 00 00 00 65 73 00 00 00 00 00 00 ........es...... backtrace: [<0000000067441602>] kstrdup+0x2d/0x60 [<00000000141cf7b7>] apply_subsystem_event_filter+0x378/0x932 [<000000009ca32334>] subsystem_filter_write+0x5a/0x90 [<0000000072da2bee>] vfs_write+0xe1/0x240 [<000000004f14f473>] ksys_write+0xb4/0x150 [<00000000a968b4a0>] do_syscall_64+0x6d/0x1e0 [<000000001a189f40>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 unreferenced object 0xffff888060c22d00 (size 64): comm "bash", pid 579, jiffies 4295096372 (age 17.752s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 e8 d7 41 80 88 ff ff ...........A.... 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000b8c1b109>] process_preds+0x243/0x1820 [<000000003972c7f0>] apply_subsystem_event_filter+0x3be/0x932 [<000000009ca32334>] subsystem_filter_write+0x5a/0x90 [<0000000072da2bee>] vfs_write+0xe1/0x240 [<000000004f14f473>] ksys_write+0xb4/0x150 [<00000000a968b4a0>] do_syscall_64+0x6d/0x1e0 [<000000001a189f40>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 unreferenced object 0xffff888041d7e800 (size 512): comm "bash", pid 579, jiffies 4295096372 (age 17.752s) hex dump (first 32 bytes): 70 bc 85 97 ff ff ff ff 0a 00 00 00 00 00 00 00 p............... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000001e04af34>] process_preds+0x71a/0x1820 [<000000003972c7f0>] apply_subsystem_event_filter+0x3be/0x932 [<000000009ca32334>] subsystem_filter_write+0x5a/0x90 [<0000000072da2bee>] vfs_write+0xe1/0x240 [<000000004f14f473>] ksys_write+0xb4/0x150 [<00000000a968b4a0>] do_syscall_64+0x6d/0x1e0 [<000000001a189f40>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Link: http://lkml.kernel.org/r/20191211091258.11310-1-keitasuzuki.park@sslab.ics.keio.ac.jp Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 404a3add43c9c ("tracing: Only add filter list when needed") Signed-off-by: Keita Suzuki Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c9a74f82b14a..bf44f6bbd0c3 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1662,7 +1662,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0); return -EINVAL; fail_mem: - kfree(filter); + __free_filter(filter); /* If any call succeeded, we still need to sync */ if (!fail) tracepoint_synchronize_unregister(); -- cgit From 106f41f5a302cb1f36c7543fae6a05de12e96fa4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 11 Dec 2019 15:44:22 -0500 Subject: tracing: Have the histogram compare functions convert to u64 first The compare functions of the histogram code would be specific for the size of the value being compared (byte, short, int, long long). It would reference the value from the array via the type of the compare, but the value was stored in a 64 bit number. This is fine for little endian machines, but for big endian machines, it would end up comparing zeros or all ones (depending on the sign) for anything but 64 bit numbers. To fix this, first derference the value as a u64 then convert it to the type being compared. Link: http://lkml.kernel.org/r/20191211103557.7bed6928@gandalf.local.home Cc: stable@vger.kernel.org Fixes: 08d43a5fa063e ("tracing: Add lock-free tracing_map") Acked-by: Tom Zanussi Reported-by: Sven Schnelle Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/tracing_map.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9a1c22310323..9e31bfc818ff 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b) #define DEFINE_TRACING_MAP_CMP_FN(type) \ static int tracing_map_cmp_##type(void *val_a, void *val_b) \ { \ - type a = *(type *)val_a; \ - type b = *(type *)val_b; \ + type a = (type)(*(u64 *)val_a); \ + type b = (type)(*(u64 *)val_b); \ \ return (a > b) ? 1 : ((a < b) ? -1 : 0); \ } -- cgit From 43cf75d96409a20ef06b756877a2e72b10a026fc Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Thu, 19 Dec 2019 14:29:53 +0800 Subject: exit: panic before exit_mm() on global init exit Currently, when global init and all threads in its thread-group have exited we panic via: do_exit() -> exit_notify() -> forget_original_parent() -> find_child_reaper() This makes it hard to extract a useable coredump for global init from a kernel crashdump because by the time we panic exit_mm() will have already released global init's mm. This patch moves the panic futher up before exit_mm() is called. As was the case previously, we only panic when global init and all its threads in the thread-group have exited. Signed-off-by: chenqiwu Acked-by: Christian Brauner Acked-by: Oleg Nesterov [christian.brauner@ubuntu.com: fix typo, rewrite commit message] Link: https://lore.kernel.org/r/1576736993-10121-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Christian Brauner --- kernel/exit.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index a46a50d67002..fc364272759d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father, } write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) { - panic("Attempted to kill init! exitcode=0x%08x\n", - father->signal->group_exit_code ?: father->exit_code); - } list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); @@ -786,6 +782,14 @@ void __noreturn do_exit(long code) acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { + /* + * If the last thread of global init has exited, panic + * immediately to get a useable coredump. + */ + if (unlikely(is_global_init(tsk))) + panic("Attempted to kill init! exitcode=0x%08x\n", + tsk->signal->group_exit_code ?: (int)code); + #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); -- cgit From 3a53acf1d9bea11b57c1f6205e3fe73f9d8a3688 Mon Sep 17 00:00:00 2001 From: Prateek Sood Date: Tue, 10 Dec 2019 09:15:16 +0000 Subject: tracing: Fix lock inversion in trace_event_enable_tgid_record() Task T2 Task T3 trace_options_core_write() subsystem_open() mutex_lock(trace_types_lock) mutex_lock(event_mutex) set_tracer_flag() trace_event_enable_tgid_record() mutex_lock(trace_types_lock) mutex_lock(event_mutex) This gives a circular dependency deadlock between trace_types_lock and event_mutex. To fix this invert the usage of trace_types_lock and event_mutex in trace_options_core_write(). This keeps the sequence of lock usage consistent. Link: http://lkml.kernel.org/r/0101016eef175e38-8ca71caf-a4eb-480d-a1e6-6f0bbc015495-000000@us-west-2.amazonses.com Cc: stable@vger.kernel.org Fixes: d914ba37d7145 ("tracing: Add support for recording tgid of tasks") Signed-off-by: Prateek Sood Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 8 ++++++++ kernel/trace/trace_events.c | 8 ++++---- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6c75410f9698..ddb7e7f5fe8d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4685,6 +4685,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { + if ((mask == TRACE_ITER_RECORD_TGID) || + (mask == TRACE_ITER_RECORD_CMD)) + lockdep_assert_held(&event_mutex); + /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; @@ -4752,6 +4756,7 @@ static int trace_set_options(struct trace_array *tr, char *option) cmp += len; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); @@ -4762,6 +4767,7 @@ static int trace_set_options(struct trace_array *tr, char *option) ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, @@ -8076,9 +8082,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (ret < 0) return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c6de3cebc127..a5b614cc3887 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -320,7 +320,8 @@ void trace_event_enable_cmd_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) @@ -334,7 +335,6 @@ void trace_event_enable_cmd_record(bool enable) clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } void trace_event_enable_tgid_record(bool enable) @@ -342,7 +342,8 @@ void trace_event_enable_tgid_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; @@ -356,7 +357,6 @@ void trace_event_enable_tgid_record(bool enable) &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } static int __ftrace_event_enable_disable(struct trace_event_file *file, -- cgit From fe6e096a5bbf73a142f09c72e7aa2835026eb1a3 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Wed, 18 Dec 2019 08:44:27 +0100 Subject: tracing: Fix endianness bug in histogram trigger At least on PA-RISC and s390 synthetic histogram triggers are failing selftests because trace_event_raw_event_synth() always writes a 64 bit values, but the reader expects a field->size sized value. On little endian machines this doesn't hurt, but on big endian this makes the reader always read zero values. Link: http://lore.kernel.org/linux-trace-devel/20191218074427.96184-4-svens@linux.ibm.com Cc: stable@vger.kernel.org Fixes: 4b147936fa509 ("tracing: Add support for 'synthetic' events") Acked-by: Tom Zanussi Signed-off-by: Sven Schnelle Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f49d1a36d3ae..f62de5f43e79 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -911,7 +911,26 @@ static notrace void trace_event_raw_event_synth(void *__data, strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = var_ref_vals[var_ref_idx + i]; + struct synth_field *field = event->fields[i]; + u64 val = var_ref_vals[var_ref_idx + i]; + + switch (field->size) { + case 1: + *(u8 *)&entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&entry->fields[n_u64] = (u32)val; + break; + + default: + entry->fields[n_u64] = val; + break; + } n_u64++; } } -- cgit From f54c7898ed1c3c9331376c0337a5049c38f66497 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 22 Dec 2019 23:37:40 +0100 Subject: bpf: Fix precision tracking for unbounded scalars Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes. Upon closer analysis, it turns out that precise scalar value tracking is missing a few precision markings for unknown scalars: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r0 = 0 1: R0_w=invP0 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (35) if r0 >= 0xf72e goto pc+0 --> only follow fallthrough 2: R0_w=invP0 R1=ctx(id=0,off=0,imm=0) R10=fp0 2: (35) if r0 >= 0x80fe0000 goto pc+0 --> only follow fallthrough 3: R0_w=invP0 R1=ctx(id=0,off=0,imm=0) R10=fp0 3: (14) w0 -= -536870912 4: R0_w=invP536870912 R1=ctx(id=0,off=0,imm=0) R10=fp0 4: (0f) r1 += r0 5: R0_w=invP536870912 R1_w=inv(id=0) R10=fp0 5: (55) if r1 != 0x104c1500 goto pc+0 --> push other branch for later analysis R0_w=invP536870912 R1_w=inv273421568 R10=fp0 6: R0_w=invP536870912 R1_w=inv273421568 R10=fp0 6: (b7) r0 = 0 7: R0=invP0 R1=inv273421568 R10=fp0 7: (76) if w1 s>= 0xffffff00 goto pc+3 --> only follow goto 11: R0=invP0 R1=inv273421568 R10=fp0 11: (95) exit 6: R0_w=invP536870912 R1_w=inv(id=0) R10=fp0 6: (b7) r0 = 0 propagating r0 7: safe processed 11 insns [...] In the analysis of the second path coming after the successful exit above, the path is being pruned at line 7. Pruning analysis found that both r0 are precise P0 and both R1 are non-precise scalars and given prior path with R1 as non-precise scalar succeeded, this one is therefore safe as well. However, problem is that given condition at insn 7 in the first run, we only followed goto and didn't push the other branch for later analysis, we've never walked the few insns in there and therefore dead-code sanitation rewrites it as goto pc-1, causing the hang depending on the skb address hitting these conditions. The issue is that R1 should have been marked as precise as well such that pruning enforces range check and conluded that new R1 is not in range of old R1. In insn 4, we mark R1 (skb) as unknown scalar via __mark_reg_unbounded() but not mark_reg_unbounded() and therefore regs->precise remains as false. Back in b5dc0163d8fd ("bpf: precise scalar_value tracking"), this was not the case since marking out of __mark_reg_unbounded() had this covered as well. Once in both are set as precise in 4 as they should have been, we conclude that given R1 was in prior fall-through path 0x104c1500 and now is completely unknown, the check at insn 7 concludes that we need to continue walking. Analysis after the fix: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r0 = 0 1: R0_w=invP0 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (35) if r0 >= 0xf72e goto pc+0 2: R0_w=invP0 R1=ctx(id=0,off=0,imm=0) R10=fp0 2: (35) if r0 >= 0x80fe0000 goto pc+0 3: R0_w=invP0 R1=ctx(id=0,off=0,imm=0) R10=fp0 3: (14) w0 -= -536870912 4: R0_w=invP536870912 R1=ctx(id=0,off=0,imm=0) R10=fp0 4: (0f) r1 += r0 5: R0_w=invP536870912 R1_w=invP(id=0) R10=fp0 5: (55) if r1 != 0x104c1500 goto pc+0 R0_w=invP536870912 R1_w=invP273421568 R10=fp0 6: R0_w=invP536870912 R1_w=invP273421568 R10=fp0 6: (b7) r0 = 0 7: R0=invP0 R1=invP273421568 R10=fp0 7: (76) if w1 s>= 0xffffff00 goto pc+3 11: R0=invP0 R1=invP273421568 R10=fp0 11: (95) exit 6: R0_w=invP536870912 R1_w=invP(id=0) R10=fp0 6: (b7) r0 = 0 7: R0_w=invP0 R1_w=invP(id=0) R10=fp0 7: (76) if w1 s>= 0xffffff00 goto pc+3 R0_w=invP0 R1_w=invP(id=0) R10=fp0 8: R0_w=invP0 R1_w=invP(id=0) R10=fp0 8: (a5) if r0 < 0x2007002a goto pc+0 9: R0_w=invP0 R1_w=invP(id=0) R10=fp0 9: (57) r0 &= -16316416 10: R0_w=invP0 R1_w=invP(id=0) R10=fp0 10: (a6) if w0 < 0x1201 goto pc+0 11: R0_w=invP0 R1_w=invP(id=0) R10=fp0 11: (95) exit 11: R0=invP0 R1=invP(id=0) R10=fp0 11: (95) exit processed 16 insns [...] Fixes: 6754172c208d ("bpf: fix precision tracking in presence of bpf2bpf calls") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191222223740.25297-1-daniel@iogearbox.net --- kernel/bpf/verifier.c | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4983940cbdca..6f63ae7a370c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(struct bpf_reg_state *reg); +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. @@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); @@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and @@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; __mark_reg_unbounded(reg); } @@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - regs += regno; - __mark_reg_unknown(regs); - /* constant backtracking is enabled for root without bpf2bpf calls */ - regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? - true : false; + __mark_reg_unknown(env, regs + regno); } -static void __mark_reg_not_init(struct bpf_reg_state *reg) +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } @@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); } #define DEF_NOT_SUBREG (0) @@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(&state->stack[spi].spilled_ptr); + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; @@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env, if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -4582,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4834,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -6982,7 +6983,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* since the register is unused, clear its state * to make further comparison simpler */ - __mark_reg_not_init(&st->regs[i]); + __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { @@ -6990,7 +6991,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { - __mark_reg_not_init(&st->stack[i].spilled_ptr); + __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } -- cgit From 66528a4575eee9f5a5270219894ab6178f146e84 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 11 Dec 2019 11:17:11 -0500 Subject: rseq: Reject unknown flags on rseq unregister It is preferrable to reject unknown flags within rseq unregistration rather than to ignore them. It is an oversight caused by the fact that the check for unknown flags is after the rseq unregister flag check. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191211161713.4490-2-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- kernel/rseq.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/rseq.c b/kernel/rseq.c index 27c48eb7de40..a4f86a9d6937 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int ret; if (flags & RSEQ_FLAG_UNREGISTER) { + if (flags & ~RSEQ_FLAG_UNREGISTER) + return -EINVAL; /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; -- cgit From d91f3057263ceb691ef527e71b41a56b17f6c869 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 20 Dec 2019 08:51:28 -0500 Subject: locking/lockdep: Fix buffer overrun problem in stack_trace[] If the lockdep code is really running out of the stack_trace entries, it is likely that buffer overrun can happen and the data immediately after stack_trace[] will be corrupted. If there is less than LOCK_TRACE_SIZE_IN_LONGS entries left before the call to save_trace(), the max_entries computation will leave it with a very large positive number because of its unsigned nature. The subsequent call to stack_trace_save() will then corrupt the data after stack_trace[]. Fix that by changing max_entries to a signed integer and check for negative value before calling stack_trace_save(). Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Bart Van Assche Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 12593b7467f9 ("locking/lockdep: Reduce space occupied by stack traces") Link: https://lkml.kernel.org/r/20191220135128.14876-1-longman@redhat.com Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 32282e7112d3..32406ef0d6a2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void) struct lock_trace *trace, *t2; struct hlist_head *hash_head; u32 hash; - unsigned int max_entries; + int max_entries; BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE); BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES); @@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void) trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries); max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries - LOCK_TRACE_SIZE_IN_LONGS; - trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); - if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES - - LOCK_TRACE_SIZE_IN_LONGS - 1) { + if (max_entries <= 0) { if (!debug_locks_off_graph_unlock()) return NULL; @@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void) return NULL; } + trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); hash = jhash(trace->entries, trace->nr_entries * sizeof(trace->entries[0]), 0); -- cgit From a33121e5487b424339636b25c35d3a180eaa5f5e Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Fri, 27 Dec 2019 03:26:27 +0100 Subject: ptp: fix the race between the release of ptp_clock and cdev In a case when a ptp chardev (like /dev/ptp0) is open but an underlying device is removed, closing this file leads to a race. This reproduces easily in a kvm virtual machine: ts# cat openptp0.c int main() { ... fp = fopen("/dev/ptp0", "r"); ... sleep(10); } ts# uname -r 5.5.0-rc3-46cf053e ts# cat /proc/cmdline ... slub_debug=FZP ts# modprobe ptp_kvm ts# ./openptp0 & [1] 670 opened /dev/ptp0, sleeping 10s... ts# rmmod ptp_kvm ts# ls /dev/ptp* ls: cannot access '/dev/ptp*': No such file or directory ts# ...woken up [ 48.010809] general protection fault: 0000 [#1] SMP [ 48.012502] CPU: 6 PID: 658 Comm: openptp0 Not tainted 5.5.0-rc3-46cf053e #25 [ 48.014624] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ... [ 48.016270] RIP: 0010:module_put.part.0+0x7/0x80 [ 48.017939] RSP: 0018:ffffb3850073be00 EFLAGS: 00010202 [ 48.018339] RAX: 000000006b6b6b6b RBX: 6b6b6b6b6b6b6b6b RCX: ffff89a476c00ad0 [ 48.018936] RDX: fffff65a08d3ea08 RSI: 0000000000000247 RDI: 6b6b6b6b6b6b6b6b [ 48.019470] ... ^^^ a slub poison [ 48.023854] Call Trace: [ 48.024050] __fput+0x21f/0x240 [ 48.024288] task_work_run+0x79/0x90 [ 48.024555] do_exit+0x2af/0xab0 [ 48.024799] ? vfs_write+0x16a/0x190 [ 48.025082] do_group_exit+0x35/0x90 [ 48.025387] __x64_sys_exit_group+0xf/0x10 [ 48.025737] do_syscall_64+0x3d/0x130 [ 48.026056] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 48.026479] RIP: 0033:0x7f53b12082f6 [ 48.026792] ... [ 48.030945] Modules linked in: ptp i6300esb watchdog [last unloaded: ptp_kvm] [ 48.045001] Fixing recursive fault but reboot is needed! This happens in: static void __fput(struct file *file) { ... if (file->f_op->release) file->f_op->release(inode, file); <<< cdev is kfree'd here if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); <<< cdev fields are accessed here Namely: __fput() posix_clock_release() kref_put(&clk->kref, delete_clock) <<< the last reference delete_clock() delete_ptp_clock() kfree(ptp) <<< cdev is embedded in ptp cdev_put module_put(p->owner) <<< *p is kfree'd, bang! Here cdev is embedded in posix_clock which is embedded in ptp_clock. The race happens because ptp_clock's lifetime is controlled by two refcounts: kref and cdev.kobj in posix_clock. This is wrong. Make ptp_clock's sysfs device a parent of cdev with cdev_device_add() created especially for such cases. This way the parent device with its ptp_clock is not released until all references to the cdev are released. This adds a requirement that an initialized but not exposed struct device should be provided to posix_clock_register() by a caller instead of a simple dev_t. This approach was adopted from the commit 72139dfa2464 ("watchdog: Fix the race between the release of watchdog_core_data and cdev"). See details of the implementation in the commit 233ed09d7fda ("chardev: add helper function to register char devs with a struct device"). Link: https://lore.kernel.org/linux-fsdevel/20191125125342.6189-1-vdronov@redhat.com/T/#u Analyzed-by: Stephen Johnston Analyzed-by: Vern Lovejoy Signed-off-by: Vladis Dronov Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 31 ++++++++++++++----------------- drivers/ptp/ptp_private.h | 2 +- include/linux/posix-clock.h | 19 +++++++++++-------- kernel/time/posix-clock.c | 31 +++++++++++++------------------ 4 files changed, 39 insertions(+), 44 deletions(-) (limited to 'kernel') diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index e60eab7f8a61..61fafe0374ce 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -166,9 +166,9 @@ static struct posix_clock_operations ptp_clock_ops = { .read = ptp_read, }; -static void delete_ptp_clock(struct posix_clock *pc) +static void ptp_clock_release(struct device *dev) { - struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); @@ -213,7 +213,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } ptp->clock.ops = ptp_clock_ops; - ptp->clock.release = delete_ptp_clock; ptp->info = info; ptp->devid = MKDEV(major, index); ptp->index = index; @@ -236,15 +235,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (err) goto no_pin_groups; - /* Create a new device in our class. */ - ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid, - ptp, ptp->pin_attr_groups, - "ptp%d", ptp->index); - if (IS_ERR(ptp->dev)) { - err = PTR_ERR(ptp->dev); - goto no_device; - } - /* Register a new PPS source. */ if (info->pps) { struct pps_source_info pps; @@ -260,8 +250,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } } - /* Create a posix clock. */ - err = posix_clock_register(&ptp->clock, ptp->devid); + /* Initialize a new device of our class in our clock structure. */ + device_initialize(&ptp->dev); + ptp->dev.devt = ptp->devid; + ptp->dev.class = ptp_class; + ptp->dev.parent = parent; + ptp->dev.groups = ptp->pin_attr_groups; + ptp->dev.release = ptp_clock_release; + dev_set_drvdata(&ptp->dev, ptp); + dev_set_name(&ptp->dev, "ptp%d", ptp->index); + + /* Create a posix clock and link it to the device. */ + err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { pr_err("failed to create posix clock\n"); goto no_clock; @@ -273,8 +273,6 @@ no_clock: if (ptp->pps_source) pps_unregister_source(ptp->pps_source); no_pps: - device_destroy(ptp_class, ptp->devid); -no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: if (ptp->kworker) @@ -304,7 +302,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp) if (ptp->pps_source) pps_unregister_source(ptp->pps_source); - device_destroy(ptp_class, ptp->devid); ptp_cleanup_pin_groups(ptp); posix_clock_unregister(&ptp->clock); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 9171d42468fd..6b97155148f1 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -28,7 +28,7 @@ struct timestamp_event_queue { struct ptp_clock { struct posix_clock clock; - struct device *dev; + struct device dev; struct ptp_clock_info *info; dev_t devid; int index; /* index into clocks.map */ diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index fe6cfdcfbc26..468328b1e1dd 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -69,29 +69,32 @@ struct posix_clock_operations { * * @ops: Functional interface to the clock * @cdev: Character device instance for this clock - * @kref: Reference count. + * @dev: Pointer to the clock's device. * @rwsem: Protects the 'zombie' field from concurrent access. * @zombie: If 'zombie' is true, then the hardware has disappeared. - * @release: A function to free the structure when the reference count reaches - * zero. May be NULL if structure is statically allocated. * * Drivers should embed their struct posix_clock within a private * structure, obtaining a reference to it during callbacks using * container_of(). + * + * Drivers should supply an initialized but not exposed struct device + * to posix_clock_register(). It is used to manage lifetime of the + * driver's private structure. It's 'release' field should be set to + * a release function for this private structure. */ struct posix_clock { struct posix_clock_operations ops; struct cdev cdev; - struct kref kref; + struct device *dev; struct rw_semaphore rwsem; bool zombie; - void (*release)(struct posix_clock *clk); }; /** * posix_clock_register() - register a new clock - * @clk: Pointer to the clock. Caller must provide 'ops' and 'release' - * @devid: Allocated device id + * @clk: Pointer to the clock. Caller must provide 'ops' field + * @dev: Pointer to the initialized device. Caller must provide + * 'release' field * * A clock driver calls this function to register itself with the * clock device subsystem. If 'clk' points to dynamically allocated @@ -100,7 +103,7 @@ struct posix_clock { * * Returns zero on success, non-zero otherwise. */ -int posix_clock_register(struct posix_clock *clk, dev_t devid); +int posix_clock_register(struct posix_clock *clk, struct device *dev); /** * posix_clock_unregister() - unregister a clock diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ec960bb939fd..200fb2d3be99 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -14,8 +14,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp) if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = { #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); -- cgit From 2882d53c9c6f3b8311d225062522f03772cf0179 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Sat, 28 Dec 2019 22:24:50 -0800 Subject: seccomp: Check that seccomp_notif is zeroed out by the user This patch is a small change in enforcement of the uapi for SECCOMP_IOCTL_NOTIF_RECV ioctl. Specifically, the datastructure which is passed (seccomp_notif) must be zeroed out. Previously any of its members could be set to nonsense values, and we would ignore it. This ensures all fields are set to their zero value. Signed-off-by: Sargun Dhillon Reviewed-by: Christian Brauner Reviewed-by: Aleksa Sarai Acked-by: Tycho Andersen Link: https://lore.kernel.org/r/20191229062451.9467-2-sargun@sargun.me Fixes: 6a21cc50f0c7 ("seccomp: add a return code to trap to userspace") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook --- kernel/seccomp.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 12d2227e5786..b6ea3dcb57bf 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter, struct seccomp_notif unotif; ssize_t ret; + /* Verify that we're not given garbage to keep struct extensible. */ + ret = check_zeroed_user(buf, sizeof(unotif)); + if (ret < 0) + return ret; + if (!ret) + return -EINVAL; + memset(&unotif, 0, sizeof(unotif)); ret = down_interruptible(&filter->notif->request); -- cgit From 02f4e01ce710fe20d2e5548d52bfdea52efd09d1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Jan 2020 19:04:57 -0500 Subject: tracing: Initialize val to zero in parse_entry of inject code gcc produces a variable may be uninitialized warning for "val" in parse_entry(). This is really a false positive, but the code is subtle enough to just initialize val to zero and it's not a fast path to worry about it. Marked for stable to remove the warning in the stable trees as well. Cc: stable@vger.kernel.org Fixes: 6c3edaf9fd6a3 ("tracing: Introduce trace event injection") Reported-by: kbuild test robot Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_inject.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index d45079ee62f8..22bcf7c51d1e 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -195,7 +195,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) unsigned long irq_flags; void *entry = NULL; int entry_size; - u64 val; + u64 val = 0; int len; entry = trace_alloc_entry(call, &entry_size); -- cgit From d2ccbccb5444e9141b33cf5399927737e9ff1c3d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Jan 2020 21:56:44 -0500 Subject: tracing: Define MCOUNT_INSN_SIZE when not defined without direct calls In order to handle direct calls along side of function graph tracer, a check is made to see if the address being traced by the function graph tracer is a direct call or not. To get the address used by direct callers, the return address is subtracted by MCOUNT_INSN_SIZE. For some archs with certain configurations, MCOUNT_INSN_SIZE is undefined here. But these should not be using direct calls anyway. Just define MCOUNT_INSN_SIZE to zero in this case. Link: https://lore.kernel.org/r/202001020219.zvE3vsty%lkp@intel.com Reported-by: kbuild test robot Fixes: ff205766dbbee ("ftrace: Fix function_graph tracer interaction with BPF trampoline") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/fgraph.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index a2659735db73..1af321dec0f1 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -96,6 +96,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, return 0; } +/* + * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct + * functions. But those archs currently don't support direct functions + * anyway, and ftrace_find_rec_direct() is just a stub for them. + * Define MCOUNT_INSN_SIZE to keep those archs compiling. + */ +#ifndef MCOUNT_INSN_SIZE +/* Make sure this only works without direct calls */ +# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +# error MCOUNT_INSN_SIZE not defined with direct calls enabled +# endif +# define MCOUNT_INSN_SIZE 0 +#endif + int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { -- cgit From b8299d362d0837ae39e87e9019ebe6b736e0f035 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Jan 2020 22:02:41 -0500 Subject: tracing: Have stack tracer compile when MCOUNT_INSN_SIZE is not defined On some archs with some configurations, MCOUNT_INSN_SIZE is not defined, and this makes the stack tracer fail to compile. Just define it to zero in this case. Link: https://lore.kernel.org/r/202001020219.zvE3vsty%lkp@intel.com Cc: stable@vger.kernel.org Fixes: 4df297129f622 ("tracing: Remove most or all of stack tracer stack size from stack_max_size") Reported-by: kbuild test robot Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4df9a209f7ca..c557f42a9397 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack) local_irq_restore(flags); } +/* Some archs may not define MCOUNT_INSN_SIZE */ +#ifndef MCOUNT_INSN_SIZE +# define MCOUNT_INSN_SIZE 0 +#endif + static void stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) -- cgit From e31f7939c1c27faa5d0e3f14519eaf7c89e8a69d Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Fri, 3 Jan 2020 11:02:48 +0800 Subject: ftrace: Avoid potential division by zero in function profiler The ftrace_profile->counter is unsigned long and do_div truncates it to 32 bits, which means it can test non-zero and be truncated to zero for division. Fix this issue by using div64_ul() instead. Link: http://lkml.kernel.org/r/20200103030248.14516-1-wenyang@linux.alibaba.com Cc: stable@vger.kernel.org Fixes: e330b3bcd8319 ("tracing: Show sample std dev in function profiling") Fixes: 34886c8bc590f ("tracing: add average time in function to function profiler") Signed-off-by: Wen Yang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ac99a3500076..9bf1f2cd515e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -526,8 +526,7 @@ static int function_stat_show(struct seq_file *m, void *v) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - avg = rec->time; - do_div(avg, rec->counter); + avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) goto out; #endif @@ -553,7 +552,8 @@ static int function_stat_show(struct seq_file *m, void *v) * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ - do_div(stddev, rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, + rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); -- cgit From 50f9ad607ea891a9308e67b81f774c71736d1098 Mon Sep 17 00:00:00 2001 From: Kaitao Cheng Date: Tue, 31 Dec 2019 05:35:30 -0800 Subject: kernel/trace: Fix do not unregister tracepoints when register sched_migrate_task fail In the function, if register_trace_sched_migrate_task() returns error, sched_switch/sched_wakeup_new/sched_wakeup won't unregister. That is why fail_deprobe_sched_switch was added. Link: http://lkml.kernel.org/r/20191231133530.2794-1-pilgrimtao@gmail.com Cc: stable@vger.kernel.org Fixes: 478142c39c8c2 ("tracing: do not grab lock in wakeup latency function tracing") Signed-off-by: Kaitao Cheng Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_sched_wakeup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 5e43b9664eca..617e297f46dc 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr) if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_migrate_task\n"); - return; + goto fail_deprobe_sched_switch; } wakeup_reset(tr); @@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr) printk(KERN_ERR "failed to start wakeup tracer\n"); return; +fail_deprobe_sched_switch: + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); fail_deprobe_wake_new: unregister_trace_sched_wakeup_new(probe_wakeup, NULL); fail_deprobe: -- cgit From 72879ee0c53e2fc17f443f7b1adcc0d5130cd934 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 21 Dec 2019 15:48:25 +0000 Subject: tracing: Fix indentation issue There is a declaration that is indented one level too deeply, remove the extraneous tab. Link: http://lkml.kernel.org/r/20191221154825.33073-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_seq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 344e4c1aa09c..87de6edafd14 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -381,7 +381,7 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { - unsigned int save_len = s->seq.len; + unsigned int save_len = s->seq.len; if (s->full) return 0; -- cgit From 84029fd04c201a4c7e0b07ba262664900f47c6f5 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Sat, 4 Jan 2020 12:59:43 -0800 Subject: memcg: account security cred as well to kmemcg The cred_jar kmem_cache is already memcg accounted in the current kernel but cred->security is not. Account cred->security to kmemcg. Recently we saw high root slab usage on our production and on further inspection, we found a buggy application leaking processes. Though that buggy application was contained within its memcg but we observe much more system memory overhead, couple of GiBs, during that period. This overhead can adversely impact the isolation on the system. One source of high overhead we found was cred->security objects, which have a lifetime of at least the life of the process which allocated them. Link: http://lkml.kernel.org/r/20191205223721.40034-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Chris Down Reviewed-by: Roman Gushchin Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cred.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index c0a4c12d38b2..9ed51b70ed80 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void) new->magic = CRED_MAGIC; #endif - if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; @@ -282,7 +282,7 @@ struct cred *prepare_creds(void) new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; validate_creds(new); return new; @@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) #ifdef CONFIG_SECURITY new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); -- cgit From e10360f815ca6367357b2c2cfef17fc663e50f7b Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 27 Dec 2019 13:50:34 -0800 Subject: bpf: cgroup: prevent out-of-order release of cgroup bpf Before commit 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself") cgroup bpf structures were released with corresponding cgroup structures. It guaranteed the hierarchical order of destruction: children were always first. It preserved attached programs from being released before their propagated copies. But with cgroup auto-detachment there are no such guarantees anymore: cgroup bpf is released as soon as the cgroup is offline and there are no live associated sockets. It means that an attached program can be detached and released, while its propagated copy is still living in the cgroup subtree. This will obviously lead to an use-after-free bug. To reproduce the issue the following script can be used: #!/bin/bash CGROOT=/sys/fs/cgroup mkdir -p ${CGROOT}/A ${CGROOT}/B ${CGROOT}/A/C sleep 1 ./test_cgrp2_attach ${CGROOT}/A egress & A_PID=$! ./test_cgrp2_attach ${CGROOT}/B egress & B_PID=$! echo $$ > ${CGROOT}/A/C/cgroup.procs iperf -s & S_PID=$! iperf -c localhost -t 100 & C_PID=$! sleep 1 echo $$ > ${CGROOT}/B/cgroup.procs echo ${S_PID} > ${CGROOT}/B/cgroup.procs echo ${C_PID} > ${CGROOT}/B/cgroup.procs sleep 1 rmdir ${CGROOT}/A/C rmdir ${CGROOT}/A sleep 1 kill -9 ${S_PID} ${C_PID} ${A_PID} ${B_PID} On the unpatched kernel the following stacktrace can be obtained: [ 33.619799] BUG: unable to handle page fault for address: ffffbdb4801ab002 [ 33.620677] #PF: supervisor read access in kernel mode [ 33.621293] #PF: error_code(0x0000) - not-present page [ 33.622754] Oops: 0000 [#1] SMP NOPTI [ 33.623202] CPU: 0 PID: 601 Comm: iperf Not tainted 5.5.0-rc2+ #23 [ 33.625545] RIP: 0010:__cgroup_bpf_run_filter_skb+0x29f/0x3d0 [ 33.635809] Call Trace: [ 33.636118] ? __cgroup_bpf_run_filter_skb+0x2bf/0x3d0 [ 33.636728] ? __switch_to_asm+0x40/0x70 [ 33.637196] ip_finish_output+0x68/0xa0 [ 33.637654] ip_output+0x76/0xf0 [ 33.638046] ? __ip_finish_output+0x1c0/0x1c0 [ 33.638576] __ip_queue_xmit+0x157/0x410 [ 33.639049] __tcp_transmit_skb+0x535/0xaf0 [ 33.639557] tcp_write_xmit+0x378/0x1190 [ 33.640049] ? _copy_from_iter_full+0x8d/0x260 [ 33.640592] tcp_sendmsg_locked+0x2a2/0xdc0 [ 33.641098] ? sock_has_perm+0x10/0xa0 [ 33.641574] tcp_sendmsg+0x28/0x40 [ 33.641985] sock_sendmsg+0x57/0x60 [ 33.642411] sock_write_iter+0x97/0x100 [ 33.642876] new_sync_write+0x1b6/0x1d0 [ 33.643339] vfs_write+0xb6/0x1a0 [ 33.643752] ksys_write+0xa7/0xe0 [ 33.644156] do_syscall_64+0x5b/0x1b0 [ 33.644605] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fix this by grabbing a reference to the bpf structure of each ancestor on the initialization of the cgroup bpf structure, and dropping the reference at the end of releasing the cgroup bpf structure. This will restore the hierarchical order of cgroup bpf releasing, without adding any operations on hot paths. Thanks to Josef Bacik for the debugging and the initial analysis of the problem. Fixes: 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself") Reported-by: Josef Bacik Signed-off-by: Roman Gushchin Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/cgroup.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4fb20ab179fe..9e43b72eb619 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp) */ static void cgroup_bpf_release(struct work_struct *work) { - struct cgroup *cgrp = container_of(work, struct cgroup, - bpf.release_work); + struct cgroup *p, *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work) mutex_unlock(&cgroup_mutex); + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_put(p); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; + struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, @@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) if (ret) return ret; + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_get(p); + for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); -- cgit From 6d4f151acf9a4f6fab09b615f246c717ddedcf0c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 6 Jan 2020 22:51:57 +0100 Subject: bpf: Fix passing modified ctx to ld/abs/ind instruction Anatoly has been fuzzing with kBdysch harness and reported a KASAN slab oob in one of the outcomes: [...] [ 77.359642] BUG: KASAN: slab-out-of-bounds in bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.360463] Read of size 4 at addr ffff8880679bac68 by task bpf/406 [ 77.361119] [ 77.361289] CPU: 2 PID: 406 Comm: bpf Not tainted 5.5.0-rc2-xfstests-00157-g2187f215eba #1 [ 77.362134] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 77.362984] Call Trace: [ 77.363249] dump_stack+0x97/0xe0 [ 77.363603] print_address_description.constprop.0+0x1d/0x220 [ 77.364251] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.365030] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.365860] __kasan_report.cold+0x37/0x7b [ 77.366365] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.366940] kasan_report+0xe/0x20 [ 77.367295] bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.367821] ? bpf_skb_load_helper_8+0xf0/0xf0 [ 77.368278] ? mark_lock+0xa3/0x9b0 [ 77.368641] ? kvm_sched_clock_read+0x14/0x30 [ 77.369096] ? sched_clock+0x5/0x10 [ 77.369460] ? sched_clock_cpu+0x18/0x110 [ 77.369876] ? bpf_skb_load_helper_8+0xf0/0xf0 [ 77.370330] ___bpf_prog_run+0x16c0/0x28f0 [ 77.370755] __bpf_prog_run32+0x83/0xc0 [ 77.371153] ? __bpf_prog_run64+0xc0/0xc0 [ 77.371568] ? match_held_lock+0x1b/0x230 [ 77.371984] ? rcu_read_lock_held+0xa1/0xb0 [ 77.372416] ? rcu_is_watching+0x34/0x50 [ 77.372826] sk_filter_trim_cap+0x17c/0x4d0 [ 77.373259] ? sock_kzfree_s+0x40/0x40 [ 77.373648] ? __get_filter+0x150/0x150 [ 77.374059] ? skb_copy_datagram_from_iter+0x80/0x280 [ 77.374581] ? do_raw_spin_unlock+0xa5/0x140 [ 77.375025] unix_dgram_sendmsg+0x33a/0xa70 [ 77.375459] ? do_raw_spin_lock+0x1d0/0x1d0 [ 77.375893] ? unix_peer_get+0xa0/0xa0 [ 77.376287] ? __fget_light+0xa4/0xf0 [ 77.376670] __sys_sendto+0x265/0x280 [ 77.377056] ? __ia32_sys_getpeername+0x50/0x50 [ 77.377523] ? lock_downgrade+0x350/0x350 [ 77.377940] ? __sys_setsockopt+0x2a6/0x2c0 [ 77.378374] ? sock_read_iter+0x240/0x240 [ 77.378789] ? __sys_socketpair+0x22a/0x300 [ 77.379221] ? __ia32_sys_socket+0x50/0x50 [ 77.379649] ? mark_held_locks+0x1d/0x90 [ 77.380059] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 77.380536] __x64_sys_sendto+0x74/0x90 [ 77.380938] do_syscall_64+0x68/0x2a0 [ 77.381324] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 77.381878] RIP: 0033:0x44c070 [...] After further debugging, turns out while in case of other helper functions we disallow passing modified ctx, the special case of ld/abs/ind instruction which has similar semantics (except r6 being the ctx argument) is missing such check. Modified ctx is impossible here as bpf_skb_load_helper_8_no_cache() and others are expecting skb fields in original position, hence, add check_ctx_reg() to reject any modified ctx. Issue was first introduced back in f1174f77b50c ("bpf/verifier: rework value tracking"). Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200106215157.3553-1-daniel@iogearbox.net --- kernel/bpf/verifier.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6f63ae7a370c..ce85e7041f0c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6264,6 +6264,7 @@ static bool may_access_skb(enum bpf_prog_type type) static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); + static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; @@ -6297,7 +6298,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check whether implicit source operand (register R6) is readable */ - err = check_reg_arg(env, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; @@ -6316,7 +6317,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (regs[BPF_REG_6].type != PTR_TO_CTX) { + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; @@ -6329,6 +6330,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + if (err < 0) + return err; + /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); -- cgit From dd499f7a7e34270208350a849ef103c0b3ae477f Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 2 Jan 2020 18:24:13 +0100 Subject: clone3: ensure copy_thread_tls is implemented copy_thread implementations handle CLONE_SETTLS by reading the TLS value from the registers containing the syscall arguments for clone. This doesn't work with clone3 since the TLS value is passed in clone_args instead. Signed-off-by: Amanieu d'Antras Cc: # 5.3.x Link: https://lore.kernel.org/r/20200102172413.654385-8-amanieu@gmail.com Signed-off-by: Christian Brauner --- kernel/fork.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 2508a4f238a3..080809560072 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2578,6 +2578,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif #ifdef __ARCH_WANT_SYS_CLONE3 + +/* + * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from + * the registers containing the syscall arguments for clone. This doesn't work + * with clone3 since the TLS value is passed in clone_args instead. + */ +#ifndef CONFIG_HAVE_COPY_THREAD_TLS +#error clone3 requires copy_thread_tls support in arch +#endif + noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) -- cgit From 51bfb1d11d6daf095addf9fe8471c20992caae0b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 8 Dec 2019 20:26:55 -0800 Subject: futex: Fix kernel-doc notation warning Fix a kernel-doc warning in kernel/futex.c by adding notation for @ret. ../kernel/futex.c:1187: warning: Function parameter or member 'ret' not described in 'wait_for_owner_exiting' Fixes: 3ef240eaff36 ("futex: Prevent exit livelock") Signed-off-by: Randy Dunlap Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/223be78c-f3c8-52df-836d-c5fb8e7907e9@infradead.org --- kernel/futex.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 03c518e9747e..0cf84c8664f2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1178,6 +1178,7 @@ out_error: /** * wait_for_owner_exiting - Block until the owner has exited + * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. -- cgit From dc8d37ed304eeeea47e65fb9edc1c6c8b0093386 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Dec 2019 20:56:04 +0100 Subject: cpu/SMT: Fix x86 link error without CONFIG_SYSFS When CONFIG_SYSFS is disabled, but CONFIG_HOTPLUG_SMT is enabled, the kernel fails to link: arch/x86/power/cpu.o: In function `hibernate_resume_nonboot_cpu_disable': (.text+0x38d): undefined reference to `cpuhp_smt_enable' arch/x86/power/hibernate.o: In function `arch_resume_nosmt': hibernate.c:(.text+0x291): undefined reference to `cpuhp_smt_enable' hibernate.c:(.text+0x29c): undefined reference to `cpuhp_smt_disable' Move the exported functions out of the #ifdef section into its own with the correct conditions. The patch that caused this is marked for stable backports, so this one may need to be backported as well. Fixes: ec527c318036 ("x86/power: Fix 'nosmt' vs hibernation triple fault during resume") Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Reviewed-by: Jiri Kosina Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20191210195614.786555-1-arnd@arndb.de --- kernel/cpu.c | 143 ++++++++++++++++++++++++++++++----------------------------- 1 file changed, 72 insertions(+), 71 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index a59cc980adad..4dc279ed3b2d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1909,6 +1909,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) } EXPORT_SYMBOL(__cpuhp_remove_state); +#ifdef CONFIG_HOTPLUG_SMT +static void cpuhp_offline_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = true; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); +} + +static void cpuhp_online_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = false; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + +int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + for_each_online_cpu(cpu) { + if (topology_is_primary_thread(cpu)) + continue; + ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (ret) + break; + /* + * As this needs to hold the cpu maps lock it's impossible + * to call device_offline() because that ends up calling + * cpu_down() which takes cpu maps lock. cpu maps lock + * needs to be held as this might race against in kernel + * abusers of the hotplug machinery (thermal management). + * + * So nothing would update device:offline state. That would + * leave the sysfs entry stale and prevent onlining after + * smt control has been changed to 'off' again. This is + * called under the sysfs hotplug lock, so it is properly + * serialized against the regular offline usage. + */ + cpuhp_offline_cpu_device(cpu); + } + if (!ret) + cpu_smt_control = ctrlval; + cpu_maps_update_done(); + return ret; +} + +int cpuhp_smt_enable(void) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + cpu_smt_control = CPU_SMT_ENABLED; + for_each_present_cpu(cpu) { + /* Skip online CPUs and CPUs on offline nodes */ + if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) + continue; + ret = _cpu_up(cpu, 0, CPUHP_ONLINE); + if (ret) + break; + /* See comment in cpuhp_smt_disable() */ + cpuhp_online_cpu_device(cpu); + } + cpu_maps_update_done(); + return ret; +} +#endif + #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t show_cpuhp_state(struct device *dev, struct device_attribute *attr, char *buf) @@ -2063,77 +2135,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { #ifdef CONFIG_HOTPLUG_SMT -static void cpuhp_offline_cpu_device(unsigned int cpu) -{ - struct device *dev = get_cpu_device(cpu); - - dev->offline = true; - /* Tell user space about the state change */ - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); -} - -static void cpuhp_online_cpu_device(unsigned int cpu) -{ - struct device *dev = get_cpu_device(cpu); - - dev->offline = false; - /* Tell user space about the state change */ - kobject_uevent(&dev->kobj, KOBJ_ONLINE); -} - -int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) -{ - int cpu, ret = 0; - - cpu_maps_update_begin(); - for_each_online_cpu(cpu) { - if (topology_is_primary_thread(cpu)) - continue; - ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); - if (ret) - break; - /* - * As this needs to hold the cpu maps lock it's impossible - * to call device_offline() because that ends up calling - * cpu_down() which takes cpu maps lock. cpu maps lock - * needs to be held as this might race against in kernel - * abusers of the hotplug machinery (thermal management). - * - * So nothing would update device:offline state. That would - * leave the sysfs entry stale and prevent onlining after - * smt control has been changed to 'off' again. This is - * called under the sysfs hotplug lock, so it is properly - * serialized against the regular offline usage. - */ - cpuhp_offline_cpu_device(cpu); - } - if (!ret) - cpu_smt_control = ctrlval; - cpu_maps_update_done(); - return ret; -} - -int cpuhp_smt_enable(void) -{ - int cpu, ret = 0; - - cpu_maps_update_begin(); - cpu_smt_control = CPU_SMT_ENABLED; - for_each_present_cpu(cpu) { - /* Skip online CPUs and CPUs on offline nodes */ - if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) - continue; - ret = _cpu_up(cpu, 0, CPUHP_ONLINE); - if (ret) - break; - /* See comment in cpuhp_smt_disable() */ - cpuhp_online_cpu_device(cpu); - } - cpu_maps_update_done(); - return ret; -} - - static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) -- cgit From f35deaff1b8eadb9897e4fb8b3edc7717f4ec6fa Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 7 Dec 2019 20:10:26 +0100 Subject: time/posix-stubs: Provide compat itimer supoprt for alpha Using compat_sys_getitimer and compat_sys_setitimer on alpha causes a link failure in the Alpha tinyconfig and other configurations that turn off CONFIG_POSIX_TIMERS. Use the same #ifdef check for the stub version as well. Fixes: 4c22ea2b9120 ("y2038: use compat_{get,set}_itimer on alpha") Reported-by: Guenter Roeck Reported-by: kbuild test robot Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Tested-by: Guenter Roeck Link: https://lore.kernel.org/r/20191207191043.656328-1-arnd@arndb.de --- kernel/time/posix-stubs.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 67df65f887ac..20c65a7d4e3a 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -151,6 +151,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT COMPAT_SYS_NI(timer_create); +#endif + +#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA) COMPAT_SYS_NI(getitimer); COMPAT_SYS_NI(setitimer); #endif -- cgit From 8379bb84be757d5df2d818509faec5d66adb861d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 16:06:14 +0000 Subject: keys: Fix request_key() cache When the key cached by request_key() and co. is cleaned up on exit(), the code looks in the wrong task_struct, and so clears the wrong cache. This leads to anomalies in key refcounting when doing, say, a kernel build on an afs volume, that then trigger kasan to report a use-after-free when the key is viewed in /proc/keys. Fix this by making exit_creds() look in the passed-in task_struct rather than in current (the task_struct cleanup code is deferred by RCU and potentially run in another task). Fixes: 7743c48e54ee ("keys: Cache result of request_key*() temporarily in task_struct") Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/cred.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index c0a4c12d38b2..56395be1c2a8 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk) put_cred(cred); #ifdef CONFIG_KEYS_REQUEST_CACHE - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; + key_put(tsk->cached_requested_key); + tsk->cached_requested_key = NULL; #endif } -- cgit From de95a991bb72e009f47e0c4bbc90fc5f594588d5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 4 Dec 2019 20:56:19 -0800 Subject: tick/sched: Annotate lockless access to last_jiffies_update syzbot (KCSAN) reported a data-race in tick_do_update_jiffies64(): BUG: KCSAN: data-race in tick_do_update_jiffies64 / tick_do_update_jiffies64 write to 0xffffffff8603d008 of 8 bytes by interrupt on cpu 1: tick_do_update_jiffies64+0x100/0x250 kernel/time/tick-sched.c:73 tick_sched_do_timer+0xd4/0xe0 kernel/time/tick-sched.c:138 tick_sched_timer+0x43/0xe0 kernel/time/tick-sched.c:1292 __run_hrtimer kernel/time/hrtimer.c:1514 [inline] __hrtimer_run_queues+0x274/0x5f0 kernel/time/hrtimer.c:1576 hrtimer_interrupt+0x22a/0x480 kernel/time/hrtimer.c:1638 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1110 [inline] smp_apic_timer_interrupt+0xdc/0x280 arch/x86/kernel/apic/apic.c:1135 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 arch_local_irq_restore arch/x86/include/asm/paravirt.h:756 [inline] kcsan_setup_watchpoint+0x1d4/0x460 kernel/kcsan/core.c:436 check_access kernel/kcsan/core.c:466 [inline] __tsan_read1 kernel/kcsan/core.c:593 [inline] __tsan_read1+0xc2/0x100 kernel/kcsan/core.c:593 kallsyms_expand_symbol.constprop.0+0x70/0x160 kernel/kallsyms.c:79 kallsyms_lookup_name+0x7f/0x120 kernel/kallsyms.c:170 insert_report_filterlist kernel/kcsan/debugfs.c:155 [inline] debugfs_write+0x14b/0x2d0 kernel/kcsan/debugfs.c:256 full_proxy_write+0xbd/0x100 fs/debugfs/file.c:225 __vfs_write+0x67/0xc0 fs/read_write.c:494 vfs_write fs/read_write.c:558 [inline] vfs_write+0x18a/0x390 fs/read_write.c:542 ksys_write+0xd5/0x1b0 fs/read_write.c:611 __do_sys_write fs/read_write.c:623 [inline] __se_sys_write fs/read_write.c:620 [inline] __x64_sys_write+0x4c/0x60 fs/read_write.c:620 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffffffff8603d008 of 8 bytes by task 0 on cpu 0: tick_do_update_jiffies64+0x2b/0x250 kernel/time/tick-sched.c:62 tick_nohz_update_jiffies kernel/time/tick-sched.c:505 [inline] tick_nohz_irq_enter kernel/time/tick-sched.c:1257 [inline] tick_irq_enter+0x139/0x1c0 kernel/time/tick-sched.c:1274 irq_enter+0x4f/0x60 kernel/softirq.c:354 entering_irq arch/x86/include/asm/apic.h:517 [inline] entering_ack_irq arch/x86/include/asm/apic.h:523 [inline] smp_apic_timer_interrupt+0x55/0x280 arch/x86/kernel/apic/apic.c:1133 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:60 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc7+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Use READ_ONCE() and WRITE_ONCE() to annotate this expected race. Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191205045619.204946-1-edumazet@google.com --- kernel/time/tick-sched.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 8b192e67aabc..a792d21cac64 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now) /* * Do a quick check without holding jiffies_lock: + * The READ_ONCE() pairs with two updates done later in this function. */ - delta = ktime_sub(now, last_jiffies_update); + delta = ktime_sub(now, READ_ONCE(last_jiffies_update)); if (delta < tick_period) return; @@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now) if (delta >= tick_period) { delta = ktime_sub(delta, tick_period); - last_jiffies_update = ktime_add(last_jiffies_update, - tick_period); + /* Pairs with the lockless read in this function. */ + WRITE_ONCE(last_jiffies_update, + ktime_add(last_jiffies_update, tick_period)); /* Slow path for long timeouts */ if (unlikely(delta >= tick_period)) { @@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now) ticks = ktime_divns(delta, incr); - last_jiffies_update = ktime_add_ns(last_jiffies_update, - incr * ticks); + /* Pairs with the lockless read in this function. */ + WRITE_ONCE(last_jiffies_update, + ktime_add_ns(last_jiffies_update, + incr * ticks)); } do_timer(++ticks); -- cgit From 0af2ffc93a4b50948f9dad2786b7f1bd253bf0b9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jan 2020 21:47:33 +0100 Subject: bpf: Fix incorrect verifier simulation of ARSH under ALU32 Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (85) call bpf_get_socket_cookie#46 1: R0_w=invP(id=0) R10=fp0 1: (57) r0 &= 808464432 2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 2: (14) w0 -= 810299440 3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 3: (c4) w0 s>>= 1 4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 4: (76) if w0 s>= 0x30303030 goto pc+216 221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 221: (95) exit processed 6 insns (limit 1000000) [...] Taking a closer look, the program was xlated as follows: # ./bpftool p d x i 12 0: (85) call bpf_get_socket_cookie#7800896 1: (bf) r6 = r0 2: (57) r6 &= 808464432 3: (14) w6 -= 810299440 4: (c4) w6 s>>= 1 5: (76) if w6 s>= 0x30303030 goto pc+216 6: (05) goto pc-1 7: (05) goto pc-1 8: (05) goto pc-1 [...] 220: (05) goto pc-1 221: (05) goto pc-1 222: (95) exit Meaning, the visible effect is very similar to f54c7898ed1c ("bpf: Fix precision tracking for unbounded scalars"), that is, the fall-through branch in the instruction 5 is considered to be never taken given the conclusion from the min/max bounds tracking in w6, and therefore the dead-code sanitation rewrites it as goto pc-1. However, real-life input disagrees with verification analysis since a soft-lockup was observed. The bug sits in the analysis of the ARSH. The definition is that we shift the target register value right by K bits through shifting in copies of its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the register into 32 bit mode, same happens after simulating the operation. However, for the case of simulating the actual ARSH, we don't take the mode into account and act as if it's always 64 bit, but location of sign bit is different: dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); Consider an unknown R0 where bpf_get_socket_cookie() (or others) would for example return 0xffff. With the above ARSH simulation, we'd see the following results: [...] 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (57) r0 &= 808464432 -> R0_runtime = 0x3030 3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 3: (14) w0 -= 810299440 -> R0_runtime = 0xcfb40000 4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 (0xffffffff) 4: (c4) w0 s>>= 1 -> R0_runtime = 0xe7da0000 5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0x7ffbfff8) [...] In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011 0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into 0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000' and means here that the simulation didn't retain the sign bit. With above logic, the updates happen on the 64 bit min/max bounds and given we coerced the register, the sign bits of the bounds are cleared as well, meaning, we need to force the simulation into s32 space for 32 bit alu mode. Verification after the fix below. We're first analyzing the fall-through branch on 32 bit signed >= test eventually leading to rejection of the program in this specific case: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r2 = 808464432 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (bf) r6 = r0 3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0 3: (57) r6 &= 808464432 4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 4: (14) w6 -= 810299440 5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 5: (c4) w6 s>>= 1 6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0xfffbfff8) 6: (76) if w6 s>= 0x30303030 goto pc+216 7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 7: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 8 insns (limit 1000000) [...] Fixes: 9cbe1f5a32dc ("bpf/verifier: improve register value range tracking with ARSH") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net --- include/linux/tnum.h | 2 +- kernel/bpf/tnum.c | 9 +++++++-- kernel/bpf/verifier.c | 13 ++++++++++--- 3 files changed, 18 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index c17af77f3fae..ea627d1ab7e3 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -30,7 +30,7 @@ struct tnum tnum_lshift(struct tnum a, u8 shift); /* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); /* Shift (arsh) a tnum right (by a fixed min_shift) */ -struct tnum tnum_arshift(struct tnum a, u8 min_shift); +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index ca52b9642943..d4f335a9a899 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } -struct tnum tnum_arshift(struct tnum a, u8 min_shift) +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ - return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); + if (insn_bitness == 32) + return TNUM((u32)(((s32)a.value) >> min_shift), + (u32)(((s32)a.mask) >> min_shift)); + else + return TNUM((s64)a.value >> min_shift, + (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ce85e7041f0c..7d530ce8719d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5049,9 +5049,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + if (insn_bitness == 32) { + dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); + dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); + } else { + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + } + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, + insn_bitness); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. -- cgit From 39e7234f00bc93613c086ae42d852d5f4147120a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 15 Jan 2020 10:43:36 -0500 Subject: locking/rwsem: Fix kernel crash when spinning on RWSEM_OWNER_UNKNOWN The commit 91d2a812dfb9 ("locking/rwsem: Make handoff writer optimistically spin on owner") will allow a recently woken up waiting writer to spin on the owner. Unfortunately, if the owner happens to be RWSEM_OWNER_UNKNOWN, the code will incorrectly spin on it leading to a kernel crash. This is fixed by passing the proper non-spinnable bits to rwsem_spin_on_owner() so that RWSEM_OWNER_UNKNOWN will be treated as a non-spinnable target. Fixes: 91d2a812dfb9 ("locking/rwsem: Make handoff writer optimistically spin on owner") Reported-by: Christoph Hellwig Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Tested-by: Christoph Hellwig Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200115154336.8679-1-longman@redhat.com --- kernel/locking/rwsem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 44e68761f432..0d9b6be9ecc8 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1226,8 +1226,8 @@ wait: * In this case, we attempt to acquire the lock again * without sleeping. */ - if ((wstate == WRITER_HANDOFF) && - (rwsem_spin_on_owner(sem, 0) == OWNER_NULL)) + if (wstate == WRITER_HANDOFF && + rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL) goto trylock_again; /* Block until there are no active lockers. */ -- cgit From da9ec3d3dd0f1240a48920be063448a2242dbd90 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 6 Jan 2020 12:03:39 +0000 Subject: perf: Correctly handle failed perf_get_aux_event() Vince reports a worrying issue: | so I was tracking down some odd behavior in the perf_fuzzer which turns | out to be because perf_even_open() sometimes returns 0 (indicating a file | descriptor of 0) even though as far as I can tell stdin is still open. ... and further the cause: | error is triggered if aux_sample_size has non-zero value. | | seems to be this line in kernel/events/core.c: | | if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) | goto err_locked; | | (note, err is never set) This seems to be a thinko in commit: ab43762ef010967e ("perf: Allow normal events to output AUX data") ... and we should probably return -EINVAL here, as this should only happen when the new event is mis-configured or does not have a compatible aux_event group leader. Fixes: ab43762ef010967e ("perf: Allow normal events to output AUX data") Reported-by: Vince Weaver Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Alexander Shishkin Tested-by: Vince Weaver --- kernel/events/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index a1f8bde19b56..2173c23c25b4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open, } } - if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) + if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) { + err = -EINVAL; goto err_locked; + } /* * Must be under the same ctx::mutex as perf_install_in_context(), -- cgit From 6b3ad6649a4c75504edeba242d3fd36b3096a57f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 15 Jan 2020 14:42:34 +0100 Subject: ptrace: reintroduce usage of subjective credentials in ptrace_has_cap() Commit 69f594a38967 ("ptrace: do not audit capability check when outputing /proc/pid/stat") introduced the ability to opt out of audit messages for accesses to various proc files since they are not violations of policy. While doing so it somehow switched the check from ns_capable() to has_ns_capability{_noaudit}(). That means it switched from checking the subjective credentials of the task to using the objective credentials. This is wrong since. ptrace_has_cap() is currently only used in ptrace_may_access() And is used to check whether the calling task (subject) has the CAP_SYS_PTRACE capability in the provided user namespace to operate on the target task (object). According to the cred.h comments this would mean the subjective credentials of the calling task need to be used. This switches ptrace_has_cap() to use security_capable(). Because we only call ptrace_has_cap() in ptrace_may_access() and in there we already have a stable reference to the calling task's creds under rcu_read_lock() there's no need to go through another series of dereferences and rcu locking done in ns_capable{_noaudit}(). As one example where this might be particularly problematic, Jann pointed out that in combination with the upcoming IORING_OP_OPENAT feature, this bug might allow unprivileged users to bypass the capability checks while asynchronously opening files like /proc/*/mem, because the capability checks for this would be performed against kernel credentials. To illustrate on the former point about this being exploitable: When io_uring creates a new context it records the subjective credentials of the caller. Later on, when it starts to do work it creates a kernel thread and registers a callback. The callback runs with kernel creds for ktask->real_cred and ktask->cred. To prevent this from becoming a full-blown 0-day io_uring will call override_cred() and override ktask->cred with the subjective credentials of the creator of the io_uring instance. With ptrace_has_cap() currently looking at ktask->real_cred this override will be ineffective and the caller will be able to open arbitray proc files as mentioned above. Luckily, this is currently not exploitable but will turn into a 0-day once IORING_OP_OPENAT{2} land in v5.6. Fix it now! Cc: Oleg Nesterov Cc: Eric Paris Cc: stable@vger.kernel.org Reviewed-by: Kees Cook Reviewed-by: Serge Hallyn Reviewed-by: Jann Horn Fixes: 69f594a38967 ("ptrace: do not audit capability check when outputing /proc/pid/stat") Signed-off-by: Christian Brauner --- kernel/ptrace.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index cb9ddcc08119..43d6179508d6 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) +static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns, + unsigned int mode) { + int ret; + if (mode & PTRACE_MODE_NOAUDIT) - return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); else - return has_ns_capability(current, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE); + + return ret == 0; } /* Returns 0 on success, -errno on denial. */ @@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(tcred->user_ns, mode)) + if (ptrace_has_cap(cred, tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -340,7 +345,7 @@ ok: mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(mm->user_ns, mode))) + !ptrace_has_cap(cred, mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); -- cgit