From dfeb0750b630b72b5d4fb2461bc7179eceb54666 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:36:31 -0800 Subject: kernfs: remove KERNFS_STATIC_NAME When a new kernfs node is created, KERNFS_STATIC_NAME is used to avoid making a separate copy of its name. It's currently only used for sysfs attributes whose filenames are required to stay accessible and unchanged. There are rare exceptions where these names are allocated and formatted dynamically but for the vast majority of cases they're consts in the rodata section. Now that kernfs is converted to use kstrdup_const() and kfree_const(), there's little point in keeping KERNFS_STATIC_NAME around. Remove it. Signed-off-by: Tejun Heo Cc: Andrzej Hajda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d5f6ec251fb2..29a7b2cc593e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3077,7 +3077,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), 0, cft->kf_ops, cft, - NULL, false, key); + NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); -- cgit v1.2.3-71-gd317 From e8e6d97c9bf734c42322dbed0f882ef11bfe7b58 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:37:23 -0800 Subject: cpuset: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. * kernel/cpuset.c::cpuset_print_task_mems_allowed() used a static buffer which is protected by a dedicated spinlock. Removed. Signed-off-by: Tejun Heo Cc: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 42 +++++++++--------------------------------- 1 file changed, 9 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index c54a1dae6c11..1d1fe9361d29 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1707,40 +1707,27 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; - ssize_t count; - char *buf, *s; int ret = 0; - count = seq_get_buf(sf, &buf); - s = buf; - spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: - s += cpulist_scnprintf(s, count, cs->cpus_allowed); + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: - s += nodelist_scnprintf(s, count, cs->mems_allowed); + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: - s += cpulist_scnprintf(s, count, cs->effective_cpus); + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: - s += nodelist_scnprintf(s, count, cs->effective_mems); + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; default: ret = -EINVAL; - goto out_unlock; } - if (s < buf + count - 1) { - *s++ = '\n'; - seq_commit(sf, s - buf); - } else { - seq_commit(sf, -1); - } -out_unlock: spin_unlock_irq(&callback_lock); return ret; } @@ -2610,8 +2597,6 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } -#define CPUSET_NODELIST_LEN (256) - /** * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed * @tsk: pointer to task_struct of some task. @@ -2621,23 +2606,16 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, */ void cpuset_print_task_mems_allowed(struct task_struct *tsk) { - /* Statically allocated to prevent using excess stack. */ - static char cpuset_nodelist[CPUSET_NODELIST_LEN]; - static DEFINE_SPINLOCK(cpuset_buffer_lock); struct cgroup *cgrp; - spin_lock(&cpuset_buffer_lock); rcu_read_lock(); cgrp = task_cs(tsk)->css.cgroup; - nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN, - tsk->mems_allowed); pr_info("%s cpuset=", tsk->comm); pr_cont_cgroup_name(cgrp); - pr_cont(" mems_allowed=%s\n", cpuset_nodelist); + pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed)); rcu_read_unlock(); - spin_unlock(&cpuset_buffer_lock); } /* @@ -2715,10 +2693,8 @@ out: /* Display task mems_allowed in /proc//status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { - seq_puts(m, "Mems_allowed:\t"); - seq_nodemask(m, &task->mems_allowed); - seq_puts(m, "\n"); - seq_puts(m, "Mems_allowed_list:\t"); - seq_nodemask_list(m, &task->mems_allowed); - seq_puts(m, "\n"); + seq_printf(m, "Mems_allowed:\t%*pb\n", + nodemask_pr_args(&task->mems_allowed)); + seq_printf(m, "Mems_allowed_list:\t%*pbl\n", + nodemask_pr_args(&task->mems_allowed)); } -- cgit v1.2.3-71-gd317 From ad853b48cb4650285e8544eebbba5bbd9274ee15 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:37:25 -0800 Subject: rcu: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/rcu/tree_plugin.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 2e850a51bb8f..0d7bbe3095ad 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -49,7 +49,6 @@ DEFINE_PER_CPU(char, rcu_cpu_has_work); static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ -static char __initdata nocb_buf[NR_CPUS * 5]; #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* @@ -2386,8 +2385,8 @@ void __init rcu_init_nohz(void) cpumask_and(rcu_nocb_mask, cpu_possible_mask, rcu_nocb_mask); } - cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); - pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); + pr_info("\tOffload RCU callbacks from CPUs: %*pbl.\n", + cpumask_pr_args(rcu_nocb_mask)); if (rcu_nocb_poll) pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); -- cgit v1.2.3-71-gd317 From 333470ee46b6851477dc9392eb71ba8ffa4f3387 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:37:28 -0800 Subject: sched: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/core.c | 10 ++++------ kernel/sched/stats.c | 11 ++--------- 2 files changed, 6 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1f37fe7f77a4..13049aac05a6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5462,9 +5462,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) { struct sched_group *group = sd->groups; - char str[256]; - cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); cpumask_clear(groupmask); printk(KERN_DEBUG "%*s domain %d: ", level, "", level); @@ -5477,7 +5475,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, return -1; } - printk(KERN_CONT "span %s level %s\n", str, sd->name); + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain " @@ -5522,9 +5521,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_or(groupmask, groupmask, sched_group_cpus(group)); - cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); - - printk(KERN_CONT " %s", str); + printk(KERN_CONT " %*pbl", + cpumask_pr_args(sched_group_cpus(group))); if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { printk(KERN_CONT " (cpu_capacity = %d)", group->sgc->capacity); diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index a476bea17fbc..87e2c9f0c33e 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -15,11 +15,6 @@ static int show_schedstat(struct seq_file *seq, void *v) { int cpu; - int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9; - char *mask_str = kmalloc(mask_len, GFP_KERNEL); - - if (mask_str == NULL) - return -ENOMEM; if (v == (void *)1) { seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); @@ -50,9 +45,8 @@ static int show_schedstat(struct seq_file *seq, void *v) for_each_domain(cpu, sd) { enum cpu_idle_type itype; - cpumask_scnprintf(mask_str, mask_len, - sched_domain_span(sd)); - seq_printf(seq, "domain%d %s", dcount++, mask_str); + seq_printf(seq, "domain%d %*pb", dcount++, + cpumask_pr_args(sched_domain_span(sd))); for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES; itype++) { seq_printf(seq, " %u %u %u %u %u %u %u %u", @@ -76,7 +70,6 @@ static int show_schedstat(struct seq_file *seq, void *v) rcu_read_unlock(); #endif } - kfree(mask_str); return 0; } -- cgit v1.2.3-71-gd317 From ffda22c1f316ff9c12f5911ac7a18ec3a49c9d02 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:37:31 -0800 Subject: time: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/time/tick-sched.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 1363d58f07e9..a4c4edac4528 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -326,13 +326,6 @@ static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, return NOTIFY_OK; } -/* - * Worst case string length in chunks of CPU range seems 2 steps - * separations: 0,2,4,6,... - * This is NR_CPUS + sizeof('\0') - */ -static char __initdata nohz_full_buf[NR_CPUS + 1]; - static int tick_nohz_init_all(void) { int err = -1; @@ -393,8 +386,8 @@ void __init tick_nohz_init(void) context_tracking_cpu_set(cpu); cpu_notifier(tick_nohz_cpu_down_callback, 0); - cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask); - pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); + pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", + cpumask_pr_args(tick_nohz_full_mask)); } #endif -- cgit v1.2.3-71-gd317 From dfbcbf42dd07b649bb02b1558e2c7150c035b4dc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:37:37 -0800 Subject: workqueue: use %*pb[l] to format bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/workqueue.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index beeeac9e0e3e..f28849394791 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3083,10 +3083,9 @@ static ssize_t wq_cpumask_show(struct device *dev, int written; mutex_lock(&wq->mutex); - written = cpumask_scnprintf(buf, PAGE_SIZE, wq->unbound_attrs->cpumask); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", + cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); - - written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); return written; } -- cgit v1.2.3-71-gd317 From 1a40243bae6fa0cc09cee40d51e258c725d897e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:37:39 -0800 Subject: tracing: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/trace.c | 6 +++--- kernel/trace/trace_seq.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 77b8dc528006..62c6506d663f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3353,12 +3353,12 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf, mutex_lock(&tracing_cpumask_update_lock); - len = cpumask_scnprintf(mask_str, count, tr->tracing_cpumask); - if (count - len < 2) { + len = snprintf(mask_str, count, "%*pb\n", + cpumask_pr_args(tr->tracing_cpumask)); + if (len >= count) { count = -EINVAL; goto out_err; } - len += sprintf(mask_str + len, "\n"); count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1); out_err: diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index f8b45d8792f9..e694c9f9efa4 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -120,7 +120,7 @@ void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, __trace_seq_init(s); - seq_buf_bitmask(&s->seq, maskp, nmaskbits); + seq_buf_printf(&s->seq, "%*pb", nmaskbits, maskp); if (unlikely(seq_buf_has_overflowed(&s->seq))) { s->seq.len = save_len; -- cgit v1.2.3-71-gd317 From 4497da6f950951b8819cd827bbebb8f214e8ecbe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:38:05 -0800 Subject: padata: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Cc: Steffen Klassert Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/padata.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/padata.c b/kernel/padata.c index 161402f0b517..b38bea9c466a 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -917,15 +917,10 @@ static ssize_t show_cpumask(struct padata_instance *pinst, else cpumask = pinst->cpumask.pcpu; - len = bitmap_scnprintf(buf, PAGE_SIZE, cpumask_bits(cpumask), - nr_cpu_ids); - if (PAGE_SIZE - len < 2) - len = -EINVAL; - else - len += sprintf(buf + len, "\n"); - + len = snprintf(buf, PAGE_SIZE, "%*pb\n", + nr_cpu_ids, cpumask_bits(cpumask)); mutex_unlock(&pinst->lock); - return len; + return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t store_cpumask(struct padata_instance *pinst, -- cgit v1.2.3-71-gd317 From c1d7f03fdd0ed600b161a7f3309e45a20af89796 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:38:10 -0800 Subject: irq: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/irq/proc.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 9dc9bfd8a678..df2f4642d1e7 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -46,10 +46,9 @@ static int show_irq_affinity(int type, struct seq_file *m, void *v) mask = desc->pending_mask; #endif if (type) - seq_cpumask_list(m, mask); + seq_printf(m, "%*pbl\n", cpumask_pr_args(mask)); else - seq_cpumask(m, mask); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); return 0; } @@ -67,8 +66,7 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) cpumask_copy(mask, desc->affinity_hint); raw_spin_unlock_irqrestore(&desc->lock, flags); - seq_cpumask(m, mask); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); free_cpumask_var(mask); return 0; @@ -186,8 +184,7 @@ static const struct file_operations irq_affinity_list_proc_fops = { static int default_affinity_show(struct seq_file *m, void *v) { - seq_cpumask(m, irq_default_affinity); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity)); return 0; } -- cgit v1.2.3-71-gd317 From ccbd59c1c104d6e42e949e2588563bfe25d9d98f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:38:13 -0800 Subject: profile: use %*pb[l] to print bitmaps including cpumasks and nodemasks printk and friends can now format bitmaps using '%*pb[l]'. cpumask and nodemask also provide cpumask_pr_args() and nodemask_pr_args() respectively which can be used to generate the two printf arguments necessary to format the specified cpu/nodemask. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/profile.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/profile.c b/kernel/profile.c index 54bf5ba26420..a7bcd28d6e9f 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -422,8 +422,7 @@ void profile_tick(int type) static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) { - seq_cpumask(m, prof_cpu_mask); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); return 0; } -- cgit v1.2.3-71-gd317 From bebf56a1b176c2e1c9efe44e7e6915532cc682cf Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:40:17 -0800 Subject: kasan: enable instrumentation of global variables This feature let us to detect accesses out of bounds of global variables. This will work as for globals in kernel image, so for globals in modules. Currently this won't work for symbols in user-specified sections (e.g. __init, __read_mostly, ...) The idea of this is simple. Compiler increases each global variable by redzone size and add constructors invoking __asan_register_globals() function. Information about global variable (address, size, size with redzone ...) passed to __asan_register_globals() so we could poison variable's redzone. This patch also forces module_alloc() to return 8*PAGE_SIZE aligned address making shadow memory handling ( kasan_module_alloc()/kasan_module_free() ) more simple. Such alignment guarantees that each shadow page backing modules address space correspond to only one module_alloc() allocation. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kasan.txt | 2 +- arch/x86/kernel/module.c | 12 +++++++++- arch/x86/mm/kasan_init_64.c | 2 +- include/linux/compiler-gcc4.h | 4 ++++ include/linux/compiler-gcc5.h | 2 ++ include/linux/kasan.h | 10 +++++++++ kernel/module.c | 2 ++ lib/Kconfig.kasan | 1 + mm/kasan/kasan.c | 52 +++++++++++++++++++++++++++++++++++++++++++ mm/kasan/kasan.h | 25 +++++++++++++++++++++ mm/kasan/report.c | 22 ++++++++++++++++++ scripts/Makefile.kasan | 2 +- 12 files changed, 132 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/Documentation/kasan.txt b/Documentation/kasan.txt index f0645a8a992f..092fc10961fe 100644 --- a/Documentation/kasan.txt +++ b/Documentation/kasan.txt @@ -9,7 +9,7 @@ a fast and comprehensive solution for finding use-after-free and out-of-bounds bugs. KASan uses compile-time instrumentation for checking every memory access, -therefore you will need a certain version of GCC >= 4.9.2 +therefore you will need a certain version of GCC > 4.9.2 Currently KASan is supported only for x86_64 architecture and requires that the kernel be built with the SLUB allocator. diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e830e61aae05..d1ac80b72c72 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -83,13 +84,22 @@ static unsigned long int get_module_load_offset(void) void *module_alloc(unsigned long size) { + void *p; + if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - return __vmalloc_node_range(size, 1, + + p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0)); + if (p && (kasan_module_alloc(p, size) < 0)) { + vfree(p); + return NULL; + } + + return p; } #ifdef CONFIG_X86_32 diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 53508708b7aa..4860906c6b9f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -196,7 +196,7 @@ void __init kasan_init(void) (unsigned long)kasan_mem_to_shadow(_end), NUMA_NO_NODE); - populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_VADDR), + populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); memset(kasan_zero_page, 0, PAGE_SIZE); diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index d1a558239b1a..769e19864632 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -85,3 +85,7 @@ #define __HAVE_BUILTIN_BSWAP16__ #endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#if GCC_VERSION >= 40902 +#define KASAN_ABI_VERSION 3 +#endif diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h index c8c565952548..efee493714eb 100644 --- a/include/linux/compiler-gcc5.h +++ b/include/linux/compiler-gcc5.h @@ -63,3 +63,5 @@ #define __HAVE_BUILTIN_BSWAP64__ #define __HAVE_BUILTIN_BSWAP16__ #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#define KASAN_ABI_VERSION 4 diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d5310eef3e38..72ba725ddf9c 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -49,8 +49,15 @@ void kasan_krealloc(const void *object, size_t new_size); void kasan_slab_alloc(struct kmem_cache *s, void *object); void kasan_slab_free(struct kmem_cache *s, void *object); +#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) + +int kasan_module_alloc(void *addr, size_t size); +void kasan_module_free(void *addr); + #else /* CONFIG_KASAN */ +#define MODULE_ALIGN 1 + static inline void kasan_unpoison_shadow(const void *address, size_t size) {} static inline void kasan_enable_current(void) {} @@ -74,6 +81,9 @@ static inline void kasan_krealloc(const void *object, size_t new_size) {} static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {} static inline void kasan_slab_free(struct kmem_cache *s, void *object) {} +static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } +static inline void kasan_module_free(void *addr) {} + #endif /* CONFIG_KASAN */ #endif /* LINUX_KASAN_H */ diff --git a/kernel/module.c b/kernel/module.c index 82dc1f899e6d..8426ad48362c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include #include @@ -1813,6 +1814,7 @@ static void unset_module_init_ro_nx(struct module *mod) { } void __weak module_memfree(void *module_region) { vfree(module_region); + kasan_module_free(module_region); } void __weak module_arch_cleanup(struct module *mod) diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 4d47d874335c..4fecaedc80a2 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -6,6 +6,7 @@ if HAVE_ARCH_KASAN config KASAN bool "KASan: runtime memory debugger" depends on SLUB_DEBUG + select CONSTRUCTORS help Enables kernel address sanitizer - runtime memory debugger, designed to find out-of-bounds accesses and use-after-free bugs. diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 799c52b9826c..78fee632a7ee 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -395,6 +396,57 @@ void kasan_kfree_large(const void *ptr) KASAN_FREE_PAGE); } +int kasan_module_alloc(void *addr, size_t size) +{ + void *ret; + size_t shadow_size; + unsigned long shadow_start; + + shadow_start = (unsigned long)kasan_mem_to_shadow(addr); + shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT, + PAGE_SIZE); + + if (WARN_ON(!PAGE_ALIGNED(shadow_start))) + return -EINVAL; + + ret = __vmalloc_node_range(shadow_size, 1, shadow_start, + shadow_start + shadow_size, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, + __builtin_return_address(0)); + return ret ? 0 : -ENOMEM; +} + +void kasan_module_free(void *addr) +{ + vfree(kasan_mem_to_shadow(addr)); +} + +static void register_global(struct kasan_global *global) +{ + size_t aligned_size = round_up(global->size, KASAN_SHADOW_SCALE_SIZE); + + kasan_unpoison_shadow(global->beg, global->size); + + kasan_poison_shadow(global->beg + aligned_size, + global->size_with_redzone - aligned_size, + KASAN_GLOBAL_REDZONE); +} + +void __asan_register_globals(struct kasan_global *globals, size_t size) +{ + int i; + + for (i = 0; i < size; i++) + register_global(&globals[i]); +} +EXPORT_SYMBOL(__asan_register_globals); + +void __asan_unregister_globals(struct kasan_global *globals, size_t size) +{ +} +EXPORT_SYMBOL(__asan_unregister_globals); + #define DEFINE_ASAN_LOAD_STORE(size) \ void __asan_load##size(unsigned long addr) \ { \ diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 1fcc1d81a9cf..4986b0acab21 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -11,6 +11,7 @@ #define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ #define KASAN_KMALLOC_REDZONE 0xFC /* redzone inside slub object */ #define KASAN_KMALLOC_FREE 0xFB /* object was freed (kmem_cache_free/kfree) */ +#define KASAN_GLOBAL_REDZONE 0xFA /* redzone for global variable */ /* * Stack redzone shadow values @@ -21,6 +22,10 @@ #define KASAN_STACK_RIGHT 0xF3 #define KASAN_STACK_PARTIAL 0xF4 +/* Don't break randconfig/all*config builds */ +#ifndef KASAN_ABI_VERSION +#define KASAN_ABI_VERSION 1 +#endif struct kasan_access_info { const void *access_addr; @@ -30,6 +35,26 @@ struct kasan_access_info { unsigned long ip; }; +/* The layout of struct dictated by compiler */ +struct kasan_source_location { + const char *filename; + int line_no; + int column_no; +}; + +/* The layout of struct dictated by compiler */ +struct kasan_global { + const void *beg; /* Address of the beginning of the global variable. */ + size_t size; /* Size of the global variable. */ + size_t size_with_redzone; /* Size of the variable + size of the red zone. 32 bytes aligned */ + const void *name; + const void *module_name; /* Name of the module where the global variable is declared. */ + unsigned long has_dynamic_init; /* This needed for C++ */ +#if KASAN_ABI_VERSION >= 4 + struct kasan_source_location *location; +#endif +}; + void kasan_report_error(struct kasan_access_info *info); void kasan_report_user_access(struct kasan_access_info *info); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 866732ef3db3..680ceedf810a 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -23,6 +23,8 @@ #include #include +#include + #include "kasan.h" #include "../slab.h" @@ -61,6 +63,7 @@ static void print_error_description(struct kasan_access_info *info) break; case KASAN_PAGE_REDZONE: case KASAN_KMALLOC_REDZONE: + case KASAN_GLOBAL_REDZONE: case 0 ... KASAN_SHADOW_SCALE_SIZE - 1: bug_type = "out of bounds access"; break; @@ -80,6 +83,20 @@ static void print_error_description(struct kasan_access_info *info) info->access_size, current->comm, task_pid_nr(current)); } +static inline bool kernel_or_module_addr(const void *addr) +{ + return (addr >= (void *)_stext && addr < (void *)_end) + || (addr >= (void *)MODULES_VADDR + && addr < (void *)MODULES_END); +} + +static inline bool init_task_stack_addr(const void *addr) +{ + return addr >= (void *)&init_thread_union.stack && + (addr <= (void *)&init_thread_union.stack + + sizeof(init_thread_union.stack)); +} + static void print_address_description(struct kasan_access_info *info) { const void *addr = info->access_addr; @@ -107,6 +124,11 @@ static void print_address_description(struct kasan_access_info *info) dump_page(page, "kasan: bad access detected"); } + if (kernel_or_module_addr(addr)) { + if (!init_task_stack_addr(addr)) + pr_err("Address belongs to variable %pS\n", addr); + } + dump_stack(); } diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 2163b8cc446e..631619b2b118 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -9,7 +9,7 @@ CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address CFLAGS_KASAN := $(call cc-option, -fsanitize=kernel-address \ -fasan-shadow-offset=$(CONFIG_KASAN_SHADOW_OFFSET) \ - --param asan-stack=1 \ + --param asan-stack=1 --param asan-globals=1 \ --param asan-instrumentation-with-call-threshold=$(call_threshold)) ifeq ($(call cc-option, $(CFLAGS_KASAN_MINIMAL) -Werror),) -- cgit v1.2.3-71-gd317 From 977ad481b66ca91e1f6492b3c5c4748c68fdee9c Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 13 Feb 2015 14:40:24 -0800 Subject: kprobes: set kprobes_all_disarmed earlier to enable re-optimization. In original code, the probed instruction doesn't get optimized after echo 0 > /sys/kernel/debug/kprobes/enabled echo 1 > /sys/kernel/debug/kprobes/enabled This is because original code checks kprobes_all_disarmed in optimize_kprobe(), but this flag is turned off after calling that function. Therefore, optimize_kprobe() will see kprobes_all_disarmed == true and doesn't do the optimization. This patch simply turns off kprobes_all_disarmed earlier to enable optimization. Signed-off-by: Wang Nan Signed-off-by: Masami Hiramatsu Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kprobes.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 2ca272f8f62e..c39790001854 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2320,6 +2320,12 @@ static void arm_all_kprobes(void) if (!kprobes_all_disarmed) goto already_enabled; + /* + * optimize_kprobe() called by arm_kprobe() checks + * kprobes_all_disarmed, so set kprobes_all_disarmed before + * arm_kprobe. + */ + kprobes_all_disarmed = false; /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; @@ -2328,7 +2334,6 @@ static void arm_all_kprobes(void) arm_kprobe(p); } - kprobes_all_disarmed = false; printk(KERN_INFO "Kprobes globally enabled\n"); already_enabled: -- cgit v1.2.3-71-gd317 From 69d54b916d83872a0a327778a01af2a096923f59 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 13 Feb 2015 14:40:26 -0800 Subject: kprobes: makes kprobes/enabled works correctly for optimized kprobes. debugfs/kprobes/enabled doesn't work correctly on optimized kprobes. Masami Hiramatsu has a test report on x86_64 platform: https://lkml.org/lkml/2015/1/19/274 This patch forces it to unoptimize kprobe if kprobes_all_disarmed is set. It also checks the flag in unregistering path for skipping unneeded disarming process when kprobes globally disarmed. Signed-off-by: Wang Nan Signed-off-by: Masami Hiramatsu Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kprobes.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c39790001854..c90e417bb963 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -869,7 +869,8 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; - unoptimize_kprobe(p, false); /* Try to unoptimize */ + /* Try to unoptimize */ + unoptimize_kprobe(p, kprobes_all_disarmed); if (!kprobe_queued(p)) { arch_disarm_kprobe(p); @@ -1571,7 +1572,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { - disarm_kprobe(orig_p, true); + /* + * If kprobes_all_disarmed is set, orig_p + * should have already been disarmed, so + * skip unneed disarming process. + */ + if (!kprobes_all_disarmed) + disarm_kprobe(orig_p, true); orig_p->flags |= KPROBE_FLAG_DISABLED; } } -- cgit v1.2.3-71-gd317