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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317