From c53593e5cb693d59d9e8b64fb3a79436bf99c3b3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Jan 2018 11:26:18 -0800 Subject: sched, cgroup: Don't reject lower cpu.max on ancestors While adding cgroup2 interface for the cpu controller, 0d5936344f30 ("sched: Implement interface for cgroup unified hierarchy") forgot to update input validation and left it to reject cpu.max config if any descendant has set a higher value. cgroup2 officially supports delegation and a descendant must not be able to restrict what its ancestors can configure. For absolute limits such as cpu.max and memory.max, this means that the config at each level should only act as the upper limit at that level and shouldn't interfere with what other cgroups can configure. This patch updates config validation on cgroup2 so that the cpu controller follows the same convention. Signed-off-by: Tejun Heo Fixes: 0d5936344f30 ("sched: Implement interface for cgroup unified hierarchy") Acked-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org # v4.15+ --- kernel/sched/core.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bf724c1952ea..1bc6a694c84f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6678,13 +6678,18 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) parent_quota = parent_b->hierarchical_quota; /* - * Ensure max(child_quota) <= parent_quota, inherit when no + * Ensure max(child_quota) <= parent_quota. On cgroup2, + * always take the min. On cgroup1, only inherit when no * limit is set: */ - if (quota == RUNTIME_INF) - quota = parent_quota; - else if (parent_quota != RUNTIME_INF && quota > parent_quota) - return -EINVAL; + if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) { + quota = min(quota, parent_quota); + } else { + if (quota == RUNTIME_INF) + quota = parent_quota; + else if (parent_quota != RUNTIME_INF && quota > parent_quota) + return -EINVAL; + } } cfs_b->hierarchical_quota = quota; -- cgit v1.2.3-59-g8ed1b From d1897c9538edafd4ae6bbd03cc075962ddde2c21 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 21 Feb 2018 11:39:22 -0800 Subject: cgroup: fix rule checking for threaded mode switching A domain cgroup isn't allowed to be turned threaded if its subtree is populated or domain controllers are enabled. cgroup_enable_threaded() depended on cgroup_can_be_thread_root() test to enforce this rule. A parent which has populated domain descendants or have domain controllers enabled can't become a thread root, so the above rules are enforced automatically. However, for the root cgroup which can host mixed domain and threaded children, cgroup_can_be_thread_root() doesn't check any of those conditions and thus first level cgroups ends up escaping those rules. This patch fixes the bug by adding explicit checks for those rules in cgroup_enable_threaded(). Reported-by: Michael Kerrisk (man-pages) Signed-off-by: Tejun Heo Fixes: 8cfd8147df67 ("cgroup: implement cgroup v2 thread support") Cc: stable@vger.kernel.org # v4.14+ --- kernel/cgroup/cgroup.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8cda3bc3ae22..4bfb2908ec15 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3183,6 +3183,16 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) if (cgroup_is_threaded(cgrp)) return 0; + /* + * If @cgroup is populated or has domain controllers enabled, it + * can't be switched. While the below cgroup_can_be_thread_root() + * test can catch the same conditions, that's only when @parent is + * not mixable, so let's check it explicitly. + */ + if (cgroup_is_populated(cgrp) || + cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) + return -EOPNOTSUPP; + /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) -- cgit v1.2.3-59-g8ed1b From fde9fc766e96c494b82931b1d270a9a751be07c0 Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Mon, 19 Feb 2018 16:55:06 +0000 Subject: signals: Move put_compat_sigset to compat.h to silence hardened usercopy Since commit afcc90f8621e ("usercopy: WARN() on slab cache usercopy region violations"), MIPS systems booting with a compat root filesystem emit a warning when copying compat siginfo to userspace: WARNING: CPU: 0 PID: 953 at mm/usercopy.c:81 usercopy_warn+0x98/0xe8 Bad or missing usercopy whitelist? Kernel memory exposure attempt detected from SLAB object 'task_struct' (offset 1432, size 16)! Modules linked in: CPU: 0 PID: 953 Comm: S01logging Not tainted 4.16.0-rc2 #10 Stack : ffffffff808c0000 0000000000000000 0000000000000001 65ac85163f3bdc4a 65ac85163f3bdc4a 0000000000000000 90000000ff667ab8 ffffffff808c0000 00000000000003f8 ffffffff808d0000 00000000000000d1 0000000000000000 000000000000003c 0000000000000000 ffffffff808c8ca8 ffffffff808d0000 ffffffff808d0000 ffffffff80810000 fffffc0000000000 ffffffff80785c30 0000000000000009 0000000000000051 90000000ff667eb0 90000000ff667db0 000000007fe0d938 0000000000000018 ffffffff80449958 0000000020052798 ffffffff808c0000 90000000ff664000 90000000ff667ab0 00000000100c0000 ffffffff80698810 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 ffffffff8010d02c 65ac85163f3bdc4a ... Call Trace: [] show_stack+0x9c/0x130 [] dump_stack+0x90/0xd0 [] __warn+0x100/0x118 [] warn_slowpath_fmt+0x4c/0x70 [] usercopy_warn+0x98/0xe8 [] __check_object_size+0xfc/0x250 [] put_compat_sigset+0x30/0x88 [] setup_rt_frame_n32+0xc4/0x160 [] do_signal+0x19c/0x230 [] do_notify_resume+0x60/0x78 [] work_notifysig+0x10/0x18 ---[ end trace 88fffbf69147f48a ]--- Commit 5905429ad856 ("fork: Provide usercopy whitelisting for task_struct") noted that: "While the blocked and saved_sigmask fields of task_struct are copied to userspace (via sigmask_to_save() and setup_rt_frame()), it is always copied with a static length (i.e. sizeof(sigset_t))." However, this is not true in the case of compat signals, whose sigset is copied by put_compat_sigset and receives size as an argument. At most call sites, put_compat_sigset is copying a sigset from the current task_struct. This triggers a warning when CONFIG_HARDENED_USERCOPY is active. However, by marking this function as static inline, the warning can be avoided because in all of these cases the size is constant at compile time, which is allowed. The only site where this is not the case is handling the rt_sigpending syscall, but there the copy is being made from a stack local variable so does not trigger the warning. Move put_compat_sigset to compat.h, and mark it static inline. This fixes the WARN on MIPS. Fixes: afcc90f8621e ("usercopy: WARN() on slab cache usercopy region violations") Signed-off-by: Matt Redfearn Acked-by: Kees Cook Cc: "Dmitry V . Levin" Cc: Al Viro Cc: kernel-hardening@lists.openwall.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18639/ Signed-off-by: James Hogan --- include/linux/compat.h | 26 ++++++++++++++++++++++++-- kernel/compat.c | 19 ------------------- 2 files changed, 24 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8a9643857c4a..c4139c7a0de0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -17,6 +17,7 @@ #include #include #include /* for aio_context_t */ +#include #include #include @@ -550,8 +551,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); -extern int put_compat_sigset(compat_sigset_t __user *compat, - const sigset_t *set, unsigned int size); + +/* + * Defined inline such that size can be compile time constant, which avoids + * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct + */ +static inline int +put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, + unsigned int size) +{ + /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ +#ifdef __BIG_ENDIAN + compat_sigset_t v; + switch (_NSIG_WORDS) { + case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; + } + return copy_to_user(compat, &v, size) ? -EFAULT : 0; +#else + return copy_to_user(compat, set, size) ? -EFAULT : 0; +#endif +} asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, diff --git a/kernel/compat.c b/kernel/compat.c index 3247fe761f60..3f5fa8902e7d 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -488,25 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) } EXPORT_SYMBOL_GPL(get_compat_sigset); -int -put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, - unsigned int size) -{ - /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ -#ifdef __BIG_ENDIAN - compat_sigset_t v; - switch (_NSIG_WORDS) { - case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; - } - return copy_to_user(compat, &v, size) ? -EFAULT : 0; -#else - return copy_to_user(compat, set, size) ? -EFAULT : 0; -#endif -} - #ifdef CONFIG_NUMA COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, compat_uptr_t __user *, pages32, -- cgit v1.2.3-59-g8ed1b From 167f5594b5efa20a26ff03b3424f793887e6b448 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 6 Mar 2018 15:56:47 +1100 Subject: kernel/memremap: Remove stale devres_free() call devm_memremap_pages() was re-worked in e8d513483300 "memremap: change devm_memremap_pages interface to use struct dev_pagemap" to take a caller allocated struct dev_pagemap as a function parameter. A call to devres_free() was left in the error cleanup path which results in a kernel panic if the remap fails for some reason. Remove it to fix the panic and let devm_memremap_pages() fail gracefully. Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...") Signed-off-by: Oliver O'Halloran Reviewed-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Signed-off-by: Dan Williams --- kernel/memremap.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/memremap.c b/kernel/memremap.c index 4dd4274cabe2..895e6b76b25e 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -427,7 +427,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) err_pfn_remap: err_radix: pgmap_radix_release(res, pgoff); - devres_free(pgmap); return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); -- cgit v1.2.3-59-g8ed1b From 3f553b308bb004eb730da8e00a28150c157c7724 Mon Sep 17 00:00:00 2001 From: Leon Yu Date: Tue, 6 Mar 2018 23:16:24 +0800 Subject: module: propagate error in modules_open() otherwise kernel can oops later in seq_release() due to dereferencing null file->private_data which is only set if seq_open() succeeds. BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 IP: seq_release+0xc/0x30 Call Trace: close_pdeo+0x37/0xd0 proc_reg_release+0x5d/0x60 __fput+0x9d/0x1d0 ____fput+0x9/0x10 task_work_run+0x75/0x90 do_exit+0x252/0xa00 do_group_exit+0x36/0xb0 SyS_exit_group+0xf/0x10 Fixes: 516fb7f2e73d ("/proc/module: use the same logic as /proc/kallsyms for address exposure") Cc: Jessica Yu Cc: Linus Torvalds Cc: stable@vger.kernel.org # 4.15+ Signed-off-by: Leon Yu Signed-off-by: Jessica Yu --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index ad2d420024f6..e42764acedb4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4228,7 +4228,7 @@ static int modules_open(struct inode *inode, struct file *file) m->private = kallsyms_show_value() ? NULL : (void *)8ul; } - return 0; + return err; } static const struct file_operations proc_modules_operations = { -- cgit v1.2.3-59-g8ed1b From bd903afeb504db5655a45bb4cf86f38be5b1bf62 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 5 Mar 2018 21:55:04 -0800 Subject: perf/core: Fix ctx_event_type in ctx_resched() In ctx_resched(), EVENT_FLEXIBLE should be sched_out when EVENT_PINNED is added. However, ctx_resched() calculates ctx_event_type before checking this condition. As a result, pinned events will NOT get higher priority than flexible events. The following shows this issue on an Intel CPU (where ref-cycles can only use one hardware counter). 1. First start: perf stat -C 0 -e ref-cycles -I 1000 2. Then, in the second console, run: perf stat -C 0 -e ref-cycles:D -I 1000 The second perf uses pinned events, which is expected to have higher priority. However, because it failed in ctx_resched(). It is never run. This patch fixes this by calculating ctx_event_type after re-evaluating event_type. Reported-by: Ephraim Park Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 487f05e18aa4 ("perf/core: Optimize event rescheduling on active contexts") Link: http://lkml.kernel.org/r/20180306055504.3283731-1-songliubraving@fb.com Signed-off-by: Ingo Molnar --- 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 96db9ae5d5af..4b838470fac4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2246,7 +2246,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, struct perf_event_context *task_ctx, enum event_type_t event_type) { - enum event_type_t ctx_event_type = event_type & EVENT_ALL; + enum event_type_t ctx_event_type; bool cpu_event = !!(event_type & EVENT_CPU); /* @@ -2256,6 +2256,8 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, if (event_type & EVENT_PINNED) event_type |= EVENT_FLEXIBLE; + ctx_event_type = event_type & EVENT_ALL; + perf_pmu_disable(cpuctx->ctx.pmu); if (task_ctx) task_ctx_sched_out(cpuctx, task_ctx, event_type); -- cgit v1.2.3-59-g8ed1b From 6b0ef92fee2a3189eba6d6b827b247cb4f6da7e9 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 9 Mar 2018 14:56:28 +0800 Subject: rtmutex: Make rt_mutex_futex_unlock() safe for irq-off callsites When running rcutorture with TREE03 config, CONFIG_PROVE_LOCKING=y, and kernel cmdline argument "rcutorture.gp_exp=1", lockdep reports a HARDIRQ-safe->HARDIRQ-unsafe deadlock: ================================ WARNING: inconsistent lock state 4.16.0-rc4+ #1 Not tainted -------------------------------- inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. takes: __schedule+0xbe/0xaf0 {IN-HARDIRQ-W} state was registered at: _raw_spin_lock+0x2a/0x40 scheduler_tick+0x47/0xf0 ... other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&rq->lock); lock(&rq->lock); *** DEADLOCK *** 1 lock held by rcu_torture_rea/724: rcu_torture_read_lock+0x0/0x70 stack backtrace: CPU: 2 PID: 724 Comm: rcu_torture_rea Not tainted 4.16.0-rc4+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-20171110_100015-anatol 04/01/2014 Call Trace: lock_acquire+0x90/0x200 ? __schedule+0xbe/0xaf0 _raw_spin_lock+0x2a/0x40 ? __schedule+0xbe/0xaf0 __schedule+0xbe/0xaf0 preempt_schedule_irq+0x2f/0x60 retint_kernel+0x1b/0x2d RIP: 0010:rcu_read_unlock_special+0x0/0x680 ? rcu_torture_read_unlock+0x60/0x60 __rcu_read_unlock+0x64/0x70 rcu_torture_read_unlock+0x17/0x60 rcu_torture_reader+0x275/0x450 ? rcutorture_booster_init+0x110/0x110 ? rcu_torture_stall+0x230/0x230 ? kthread+0x10e/0x130 kthread+0x10e/0x130 ? kthread_create_worker_on_cpu+0x70/0x70 ? call_usermodehelper_exec_async+0x11a/0x150 ret_from_fork+0x3a/0x50 This happens with the following even sequence: preempt_schedule_irq(); local_irq_enable(); __schedule(): local_irq_disable(); // irq off ... rcu_note_context_switch(): rcu_note_preempt_context_switch(): rcu_read_unlock_special(): local_irq_save(flags); ... raw_spin_unlock_irqrestore(...,flags); // irq remains off rt_mutex_futex_unlock(): raw_spin_lock_irq(); ... raw_spin_unlock_irq(); // accidentally set irq on rq_lock(): raw_spin_lock(); // acquiring rq->lock with irq on which means rq->lock becomes a HARDIRQ-unsafe lock, which can cause deadlocks in scheduler code. This problem was introduced by commit 02a7c234e540 ("rcu: Suppress lockdep false-positive ->boost_mtx complaints"). That brought the user of rt_mutex_futex_unlock() with irq off. To fix this, replace the *lock_irq() in rt_mutex_futex_unlock() with *lock_irq{save,restore}() to make it safe to call rt_mutex_futex_unlock() with irq off. Fixes: 02a7c234e540 ("rcu: Suppress lockdep false-positive ->boost_mtx complaints") Signed-off-by: Boqun Feng Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Lai Jiangshan Cc: Steven Rostedt Cc: Josh Triplett Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Link: https://lkml.kernel.org/r/20180309065630.8283-1-boqun.feng@gmail.com --- kernel/locking/rtmutex.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 65cc0cb984e6..940633c63254 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1616,11 +1616,12 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { DEFINE_WAKE_Q(wake_q); + unsigned long flags; bool postunlock; - raw_spin_lock_irq(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); postunlock = __rt_mutex_futex_unlock(lock, &wake_q); - raw_spin_unlock_irq(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); if (postunlock) rt_mutex_postunlock(&wake_q); -- cgit v1.2.3-59-g8ed1b From 0862ca422b79cb5aa70823ee0f07f6b468f86070 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 9 Mar 2018 15:50:59 -0800 Subject: bug: use %pB in BUG and stack protector failure The BUG and stack protector reports were still using a raw %p. This changes it to %pB for more meaningful output. Link: http://lkml.kernel.org/r/20180301225704.GA34198@beast Fixes: ad67b74d2469 ("printk: hash addresses printed with %p") Signed-off-by: Kees Cook Reviewed-by: Andrew Morton Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Richard Weinberger , Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 2 +- lib/bug.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 2cfef408fec9..4b794f1d8561 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -640,7 +640,7 @@ device_initcall(register_warn_debugfs); */ __visible void __stack_chk_fail(void) { - panic("stack-protector: Kernel stack is corrupted in: %p\n", + panic("stack-protector: Kernel stack is corrupted in: %pB\n", __builtin_return_address(0)); } EXPORT_SYMBOL(__stack_chk_fail); diff --git a/lib/bug.c b/lib/bug.c index c1b0fad31b10..44f432cb064d 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -191,7 +191,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (file) pr_crit("kernel BUG at %s:%u!\n", file, line); else - pr_crit("Kernel BUG at %p [verbose debug info unavailable]\n", + pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n", (void *)bugaddr); return BUG_TRAP_TYPE_BUG; -- cgit v1.2.3-59-g8ed1b From b6b76dd62c56f257cdd30900ed22668c42a74030 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 12 Mar 2018 19:00:49 +0900 Subject: error-injection: Fix to prohibit jump optimization Since the kprobe which was optimized by jump can not change the execution path, the kprobe for error-injection must not be optimized. To prohibit it, set a dummy post-handler as officially stated in Documentation/kprobes.txt. Fixes: 4b1a29a7f542 ("error-injection: Support fault injection framework") Signed-off-by: Masami Hiramatsu Signed-off-by: Daniel Borkmann --- kernel/fail_function.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 21b0122cb39c..1d5632d8bbcc 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -14,6 +14,15 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs); +static void fei_post_handler(struct kprobe *kp, struct pt_regs *regs, + unsigned long flags) +{ + /* + * A dummy post handler is required to prohibit optimizing, because + * jump optimization does not support execution path overriding. + */ +} + struct fei_attr { struct list_head list; struct kprobe kp; @@ -56,6 +65,7 @@ static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr) return NULL; } attr->kp.pre_handler = fei_kprobe_handler; + attr->kp.post_handler = fei_post_handler; attr->retval = adjust_error_retval(addr, 0); INIT_LIST_HEAD(&attr->list); } -- cgit v1.2.3-59-g8ed1b From 537f4146c53c95aac977852b371bafb9c6755ee1 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 6 Mar 2018 15:35:43 +0530 Subject: workqueue: use put_device() instead of kfree() Never directly free @dev after calling device_register(), even if it returned an error! Always use put_device() to give up the reference initialized in this function instead. Signed-off-by: Arvind Yadav Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bb9a519cbf50..ccd1080dd6e7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5337,7 +5337,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) ret = device_register(&wq_dev->dev); if (ret) { - kfree(wq_dev); + put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } -- cgit v1.2.3-59-g8ed1b From 6417250d3f894e66a68ba1cd93676143f2376a6f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 6 Mar 2018 19:34:42 -0800 Subject: workqueue: remove unused cancel_work() Found this by accident. There are no usages of bare cancel_work() in current kernel source. Signed-off-by: Stephen Hemminger Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 - kernel/workqueue.c | 8 -------- 2 files changed, 9 deletions(-) (limited to 'kernel') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bc0cda180c8b..0c3301421c57 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -456,7 +456,6 @@ extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); -extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ccd1080dd6e7..6ec6ba65127b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3018,14 +3018,6 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) return ret; } -/* - * See cancel_delayed_work() - */ -bool cancel_work(struct work_struct *work) -{ - return __cancel_work(work, false); -} - /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel -- cgit v1.2.3-59-g8ed1b From af1d830bf32b27b387b97c8b29dc09e306a9ff7f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 14 Mar 2018 10:24:20 -0500 Subject: jump_label: Fix sparc64 warning The kbuild test robot reported the following warning on sparc64: kernel/jump_label.c: In function '__jump_label_update': kernel/jump_label.c:376:51: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] WARN_ONCE(1, "can't patch jump_label at %pS", (void *)entry->code); On sparc64, the jump_label entry->code field is of type u32, but pointers are 64-bit. Silence the warning by casting entry->code to an unsigned long before casting it to a pointer. This is also what the sparc jump label code does. Fixes: dc1dd184c2f0 ("jump_label: Warn on failed jump_label patching attempt") Reported-by: kbuild test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Jason Baron Cc: Borislav Petkov Cc: "David S . Miller" Link: https://lkml.kernel.org/r/c966fed42be6611254a62d46579ec7416548d572.1521041026.git.jpoimboe@redhat.com --- kernel/jump_label.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 52a0a7af8640..e7214093dcd1 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -373,7 +373,8 @@ static void __jump_label_update(struct static_key *key, if (kernel_text_address(entry->code)) arch_jump_label_transform(entry, jump_label_type(entry)); else - WARN_ONCE(1, "can't patch jump_label at %pS", (void *)entry->code); + WARN_ONCE(1, "can't patch jump_label at %pS", + (void *)(unsigned long)entry->code); } } } -- cgit v1.2.3-59-g8ed1b From f005afede992e265bb98534b86912bb669ccd0d2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 20 Mar 2018 11:19:17 -0700 Subject: trace/bpf: remove helper bpf_perf_prog_read_value from tracepoint type programs Commit 4bebdc7a85aa ("bpf: add helper bpf_perf_prog_read_value") added helper bpf_perf_prog_read_value so that perf_event type program can read event counter and enabled/running time. This commit, however, introduced a bug which allows this helper for tracepoint type programs. This is incorrect as bpf_perf_prog_read_value needs to access perf_event through its bpf_perf_event_data_kern type context, which is not available for tracepoint type program. This patch fixed the issue by separating bpf_func_proto between tracepoint and perf_event type programs and removed bpf_perf_prog_read_value from tracepoint func prototype. Fixes: 4bebdc7a85aa ("bpf: add helper bpf_perf_prog_read_value") Reported-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 68 ++++++++++++++++++++++++++++-------------------- 1 file changed, 40 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c0a9e310d715..01e6b3a38871 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -661,7 +661,41 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, +static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_perf_event_output: + return &bpf_perf_event_output_proto_tp; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto_tp; + default: + return tracing_func_proto(func_id); + } +} + +static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + + BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); + return true; +} + +const struct bpf_verifier_ops tracepoint_verifier_ops = { + .get_func_proto = tp_prog_func_proto, + .is_valid_access = tp_prog_is_valid_access, +}; + +const struct bpf_prog_ops tracepoint_prog_ops = { +}; + +BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; @@ -678,8 +712,8 @@ clear: return err; } -static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { - .func = bpf_perf_prog_read_value_tp, +static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { + .func = bpf_perf_prog_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -687,7 +721,7 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { .arg3_type = ARG_CONST_SIZE, }; -static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) +static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_perf_event_output: @@ -695,34 +729,12 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_perf_prog_read_value: - return &bpf_perf_prog_read_value_proto_tp; + return &bpf_perf_prog_read_value_proto; default: return tracing_func_proto(func_id); } } -static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, - struct bpf_insn_access_aux *info) -{ - if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - - BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); - return true; -} - -const struct bpf_verifier_ops tracepoint_verifier_ops = { - .get_func_proto = tp_prog_func_proto, - .is_valid_access = tp_prog_is_valid_access, -}; - -const struct bpf_prog_ops tracepoint_prog_ops = { -}; - static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { @@ -779,7 +791,7 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, } const struct bpf_verifier_ops perf_event_verifier_ops = { - .get_func_proto = tp_prog_func_proto, + .get_func_proto = pe_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; -- cgit v1.2.3-59-g8ed1b From 0fa4fe85f4724fff89b09741c437cbee9cf8b008 Mon Sep 17 00:00:00 2001 From: Chenbo Feng Date: Mon, 19 Mar 2018 17:57:27 -0700 Subject: bpf: skip unnecessary capability check The current check statement in BPF syscall will do a capability check for CAP_SYS_ADMIN before checking sysctl_unprivileged_bpf_disabled. This code path will trigger unnecessary security hooks on capability checking and cause false alarms on unprivileged process trying to get CAP_SYS_ADMIN access. This can be resolved by simply switch the order of the statement and CAP_SYS_ADMIN is not required anyway if unprivileged bpf syscall is allowed. Signed-off-by: Chenbo Feng Acked-by: Lorenzo Colitti Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e24aa3241387..43f95d190eea 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1845,7 +1845,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz union bpf_attr attr = {}; int err; - if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled) + if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; err = check_uarg_tail_zero(uattr, sizeof(attr), size); -- cgit v1.2.3-59-g8ed1b