summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-05-20 22:31:33 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-05-20 22:31:33 -0700
commit5469dc270cd44c451590d40c031e6a71c1f637e8 (patch)
tree5ca6330c2d754dbe82bfa75964a7f828f364e48f /kernel
parent2f37dd131c5d3a2eac21cd5baf80658b1b02a8ac (diff)
parentea9b50133ffebbd580cb5cd0aa222784d7a2fcb1 (diff)
downloadlinux-5469dc270cd44c451590d40c031e6a71c1f637e8.tar.bz2
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton: - the rest of MM - KASAN updates - procfs updates - exit, fork updates - printk updates - lib/ updates - radix-tree testsuite updates - checkpatch updates - kprobes updates - a few other misc bits * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits) samples/kprobes: print out the symbol name for the hooks samples/kprobes: add a new module parameter kprobes: add the "tls" argument for j_do_fork init/main.c: simplify initcall_blacklisted() fs/efs/super.c: fix return value checkpatch: improve --git <commit-count> shortcut checkpatch: reduce number of `git log` calls with --git checkpatch: add support to check already applied git commits checkpatch: add --list-types to show message types to show or ignore checkpatch: advertise the --fix and --fix-inplace options more checkpatch: whine about ACCESS_ONCE checkpatch: add test for keywords not starting on tabstops checkpatch: improve CONSTANT_COMPARISON test for structure members checkpatch: add PREFER_IS_ENABLED test lib/GCD.c: use binary GCD algorithm instead of Euclidean radix-tree: free up the bottom bit of exceptional entries for reuse dax: move RADIX_DAX_ definitions to dax.c radix-tree: make radix_tree_descend() more useful radix-tree: introduce radix_tree_replace_clear_tags() radix-tree: tidy up __radix_tree_create() ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/fork.c54
-rw-r--r--kernel/irq/irqdomain.c7
-rw-r--r--kernel/kexec_core.c1
-rw-r--r--kernel/panic.c6
-rw-r--r--kernel/printk/Makefile1
-rw-r--r--kernel/printk/internal.h57
-rw-r--r--kernel/printk/nmi.c260
-rw-r--r--kernel/printk/printk.c31
-rw-r--r--kernel/sysctl_binary.c23
10 files changed, 383 insertions, 59 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index fd90195667e1..75b34fe835b2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -746,7 +746,7 @@ void do_exit(long code)
disassociate_ctty(1);
exit_task_namespaces(tsk);
exit_task_work(tsk);
- exit_thread();
+ exit_thread(tsk);
/*
* Flush inherited counters to the parent - before the parent
diff --git a/kernel/fork.c b/kernel/fork.c
index 3e8451527cbe..103d78fd8f75 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -699,6 +699,26 @@ void __mmdrop(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(__mmdrop);
+static inline void __mmput(struct mm_struct *mm)
+{
+ VM_BUG_ON(atomic_read(&mm->mm_users));
+
+ uprobe_clear_state(mm);
+ exit_aio(mm);
+ ksm_exit(mm);
+ khugepaged_exit(mm); /* must run before exit_mmap */
+ exit_mmap(mm);
+ set_mm_exe_file(mm, NULL);
+ if (!list_empty(&mm->mmlist)) {
+ spin_lock(&mmlist_lock);
+ list_del(&mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
+ mmdrop(mm);
+}
+
/*
* Decrement the use count and release all resources for an mm.
*/
@@ -706,24 +726,24 @@ void mmput(struct mm_struct *mm)
{
might_sleep();
+ if (atomic_dec_and_test(&mm->mm_users))
+ __mmput(mm);
+}
+EXPORT_SYMBOL_GPL(mmput);
+
+static void mmput_async_fn(struct work_struct *work)
+{
+ struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+ __mmput(mm);
+}
+
+void mmput_async(struct mm_struct *mm)
+{
if (atomic_dec_and_test(&mm->mm_users)) {
- uprobe_clear_state(mm);
- exit_aio(mm);
- ksm_exit(mm);
- khugepaged_exit(mm); /* must run before exit_mmap */
- exit_mmap(mm);
- set_mm_exe_file(mm, NULL);
- if (!list_empty(&mm->mmlist)) {
- spin_lock(&mmlist_lock);
- list_del(&mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- if (mm->binfmt)
- module_put(mm->binfmt->module);
- mmdrop(mm);
+ INIT_WORK(&mm->async_put_work, mmput_async_fn);
+ schedule_work(&mm->async_put_work);
}
}
-EXPORT_SYMBOL_GPL(mmput);
/**
* set_mm_exe_file - change a reference to the mm's executable file
@@ -1470,7 +1490,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (IS_ERR(pid)) {
retval = PTR_ERR(pid);
- goto bad_fork_cleanup_io;
+ goto bad_fork_cleanup_thread;
}
}
@@ -1632,6 +1652,8 @@ bad_fork_cancel_cgroup:
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
+bad_fork_cleanup_thread:
+ exit_thread(p);
bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index d65f6f31a5b3..8798b6c9e945 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -139,12 +139,7 @@ void irq_domain_remove(struct irq_domain *domain)
{
mutex_lock(&irq_domain_mutex);
- /*
- * radix_tree_delete() takes care of destroying the root
- * node when all entries are removed. Shout if there are
- * any mappings left.
- */
- WARN_ON(domain->revmap_tree.height);
+ WARN_ON(!radix_tree_empty(&domain->revmap_tree));
list_del(&domain->link);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 1c03dfb4abfd..d5d408252992 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -893,6 +893,7 @@ void crash_kexec(struct pt_regs *regs)
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
if (old_cpu == PANIC_CPU_INVALID) {
/* This is the 1st CPU which comes here, so go ahead. */
+ printk_nmi_flush_on_panic();
__crash_kexec(regs);
/*
diff --git a/kernel/panic.c b/kernel/panic.c
index 535c96510a44..8aa74497cc5a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -160,8 +160,10 @@ void panic(const char *fmt, ...)
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
- if (!crash_kexec_post_notifiers)
+ if (!crash_kexec_post_notifiers) {
+ printk_nmi_flush_on_panic();
__crash_kexec(NULL);
+ }
/*
* Note smp_send_stop is the usual smp shutdown function, which
@@ -176,6 +178,8 @@ void panic(const char *fmt, ...)
*/
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+ /* Call flush even twice. It tries harder with a single online CPU */
+ printk_nmi_flush_on_panic();
kmsg_dump(KMSG_DUMP_PANIC);
/*
diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile
index 85405bdcf2b3..abb0042a427b 100644
--- a/kernel/printk/Makefile
+++ b/kernel/printk/Makefile
@@ -1,2 +1,3 @@
obj-y = printk.o
+obj-$(CONFIG_PRINTK_NMI) += nmi.o
obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
new file mode 100644
index 000000000000..7fd2838fa417
--- /dev/null
+++ b/kernel/printk/internal.h
@@ -0,0 +1,57 @@
+/*
+ * internal.h - printk internal definitions
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/percpu.h>
+
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
+
+int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
+
+#ifdef CONFIG_PRINTK_NMI
+
+extern raw_spinlock_t logbuf_lock;
+
+/*
+ * printk() could not take logbuf_lock in NMI context. Instead,
+ * it temporary stores the strings into a per-CPU buffer.
+ * The alternative implementation is chosen transparently
+ * via per-CPU variable.
+ */
+DECLARE_PER_CPU(printk_func_t, printk_func);
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+{
+ return this_cpu_read(printk_func)(fmt, args);
+}
+
+extern atomic_t nmi_message_lost;
+static inline int get_nmi_message_lost(void)
+{
+ return atomic_xchg(&nmi_message_lost, 0);
+}
+
+#else /* CONFIG_PRINTK_NMI */
+
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+{
+ return vprintk_default(fmt, args);
+}
+
+static inline int get_nmi_message_lost(void)
+{
+ return 0;
+}
+
+#endif /* CONFIG_PRINTK_NMI */
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
new file mode 100644
index 000000000000..b69eb8a2876f
--- /dev/null
+++ b/kernel/printk/nmi.c
@@ -0,0 +1,260 @@
+/*
+ * nmi.c - Safe printk in NMI context
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+#include <linux/debug_locks.h>
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+#include <linux/irq_work.h>
+#include <linux/printk.h>
+
+#include "internal.h"
+
+/*
+ * printk() could not take logbuf_lock in NMI context. Instead,
+ * it uses an alternative implementation that temporary stores
+ * the strings into a per-CPU buffer. The content of the buffer
+ * is later flushed into the main ring buffer via IRQ work.
+ *
+ * The alternative implementation is chosen transparently
+ * via @printk_func per-CPU variable.
+ *
+ * The implementation allows to flush the strings also from another CPU.
+ * There are situations when we want to make sure that all buffers
+ * were handled or when IRQs are blocked.
+ */
+DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
+static int printk_nmi_irq_ready;
+atomic_t nmi_message_lost;
+
+#define NMI_LOG_BUF_LEN ((1 << CONFIG_NMI_LOG_BUF_SHIFT) - \
+ sizeof(atomic_t) - sizeof(struct irq_work))
+
+struct nmi_seq_buf {
+ atomic_t len; /* length of written data */
+ struct irq_work work; /* IRQ work that flushes the buffer */
+ unsigned char buffer[NMI_LOG_BUF_LEN];
+};
+static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
+
+/*
+ * Safe printk() for NMI context. It uses a per-CPU buffer to
+ * store the message. NMIs are not nested, so there is always only
+ * one writer running. But the buffer might get flushed from another
+ * CPU, so we need to be careful.
+ */
+static int vprintk_nmi(const char *fmt, va_list args)
+{
+ struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
+ int add = 0;
+ size_t len;
+
+again:
+ len = atomic_read(&s->len);
+
+ if (len >= sizeof(s->buffer)) {
+ atomic_inc(&nmi_message_lost);
+ return 0;
+ }
+
+ /*
+ * Make sure that all old data have been read before the buffer was
+ * reseted. This is not needed when we just append data.
+ */
+ if (!len)
+ smp_rmb();
+
+ add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
+
+ /*
+ * Do it once again if the buffer has been flushed in the meantime.
+ * Note that atomic_cmpxchg() is an implicit memory barrier that
+ * makes sure that the data were written before updating s->len.
+ */
+ if (atomic_cmpxchg(&s->len, len, len + add) != len)
+ goto again;
+
+ /* Get flushed in a more safe context. */
+ if (add && printk_nmi_irq_ready) {
+ /* Make sure that IRQ work is really initialized. */
+ smp_rmb();
+ irq_work_queue(&s->work);
+ }
+
+ return add;
+}
+
+/*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end)
+{
+ const char *buf = s->buffer + start;
+
+ /*
+ * The buffers are flushed in NMI only on panic. The messages must
+ * go only into the ring buffer at this stage. Consoles will get
+ * explicitly called later when a crashdump is not generated.
+ */
+ if (in_nmi())
+ printk_deferred("%.*s", (end - start) + 1, buf);
+ else
+ printk("%.*s", (end - start) + 1, buf);
+
+}
+
+/*
+ * Flush data from the associated per_CPU buffer. The function
+ * can be called either via IRQ work or independently.
+ */
+static void __printk_nmi_flush(struct irq_work *work)
+{
+ static raw_spinlock_t read_lock =
+ __RAW_SPIN_LOCK_INITIALIZER(read_lock);
+ struct nmi_seq_buf *s = container_of(work, struct nmi_seq_buf, work);
+ unsigned long flags;
+ size_t len, size;
+ int i, last_i;
+
+ /*
+ * The lock has two functions. First, one reader has to flush all
+ * available message to make the lockless synchronization with
+ * writers easier. Second, we do not want to mix messages from
+ * different CPUs. This is especially important when printing
+ * a backtrace.
+ */
+ raw_spin_lock_irqsave(&read_lock, flags);
+
+ i = 0;
+more:
+ len = atomic_read(&s->len);
+
+ /*
+ * This is just a paranoid check that nobody has manipulated
+ * the buffer an unexpected way. If we printed something then
+ * @len must only increase.
+ */
+ if (i && i >= len)
+ pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
+ i, len);
+
+ if (!len)
+ goto out; /* Someone else has already flushed the buffer. */
+
+ /* Make sure that data has been written up to the @len */
+ smp_rmb();
+
+ size = min(len, sizeof(s->buffer));
+ last_i = i;
+
+ /* Print line by line. */
+ for (; i < size; i++) {
+ if (s->buffer[i] == '\n') {
+ print_nmi_seq_line(s, last_i, i);
+ last_i = i + 1;
+ }
+ }
+ /* Check if there was a partial line. */
+ if (last_i < size) {
+ print_nmi_seq_line(s, last_i, size - 1);
+ pr_cont("\n");
+ }
+
+ /*
+ * Check that nothing has got added in the meantime and truncate
+ * the buffer. Note that atomic_cmpxchg() is an implicit memory
+ * barrier that makes sure that the data were copied before
+ * updating s->len.
+ */
+ if (atomic_cmpxchg(&s->len, len, 0) != len)
+ goto more;
+
+out:
+ raw_spin_unlock_irqrestore(&read_lock, flags);
+}
+
+/**
+ * printk_nmi_flush - flush all per-cpu nmi buffers.
+ *
+ * The buffers are flushed automatically via IRQ work. This function
+ * is useful only when someone wants to be sure that all buffers have
+ * been flushed at some point.
+ */
+void printk_nmi_flush(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ __printk_nmi_flush(&per_cpu(nmi_print_seq, cpu).work);
+}
+
+/**
+ * printk_nmi_flush_on_panic - flush all per-cpu nmi buffers when the system
+ * goes down.
+ *
+ * Similar to printk_nmi_flush() but it can be called even in NMI context when
+ * the system goes down. It does the best effort to get NMI messages into
+ * the main ring buffer.
+ *
+ * Note that it could try harder when there is only one CPU online.
+ */
+void printk_nmi_flush_on_panic(void)
+{
+ /*
+ * Make sure that we could access the main ring buffer.
+ * Do not risk a double release when more CPUs are up.
+ */
+ if (in_nmi() && raw_spin_is_locked(&logbuf_lock)) {
+ if (num_online_cpus() > 1)
+ return;
+
+ debug_locks_off();
+ raw_spin_lock_init(&logbuf_lock);
+ }
+
+ printk_nmi_flush();
+}
+
+void __init printk_nmi_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct nmi_seq_buf *s = &per_cpu(nmi_print_seq, cpu);
+
+ init_irq_work(&s->work, __printk_nmi_flush);
+ }
+
+ /* Make sure that IRQ works are initialized before enabling. */
+ smp_wmb();
+ printk_nmi_irq_ready = 1;
+
+ /* Flush pending messages that did not have scheduled IRQ works. */
+ printk_nmi_flush();
+}
+
+void printk_nmi_enter(void)
+{
+ this_cpu_write(printk_func, vprintk_nmi);
+}
+
+void printk_nmi_exit(void)
+{
+ this_cpu_write(printk_func, vprintk_default);
+}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index bfbf284e4218..60cdf6386763 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -55,6 +55,7 @@
#include "console_cmdline.h"
#include "braille.h"
+#include "internal.h"
int console_printk[4] = {
CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */
@@ -244,7 +245,7 @@ __packed __aligned(4)
* within the scheduler's rq lock. It must be released before calling
* console_unlock() or anything else that might wake up a process.
*/
-static DEFINE_RAW_SPINLOCK(logbuf_lock);
+DEFINE_RAW_SPINLOCK(logbuf_lock);
#ifdef CONFIG_PRINTK
DECLARE_WAIT_QUEUE_HEAD(log_wait);
@@ -1616,6 +1617,7 @@ asmlinkage int vprintk_emit(int facility, int level,
unsigned long flags;
int this_cpu;
int printed_len = 0;
+ int nmi_message_lost;
bool in_sched = false;
/* cpu currently holding logbuf_lock in this function */
static unsigned int logbuf_cpu = UINT_MAX;
@@ -1666,6 +1668,15 @@ asmlinkage int vprintk_emit(int facility, int level,
strlen(recursion_msg));
}
+ nmi_message_lost = get_nmi_message_lost();
+ if (unlikely(nmi_message_lost)) {
+ text_len = scnprintf(textbuf, sizeof(textbuf),
+ "BAD LUCK: lost %d message(s) from NMI context!",
+ nmi_message_lost);
+ printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
+ NULL, 0, textbuf, text_len);
+ }
+
/*
* The printf needs to come first; we need the syslog
* prefix which might be passed-in as a parameter.
@@ -1807,14 +1818,6 @@ int vprintk_default(const char *fmt, va_list args)
}
EXPORT_SYMBOL_GPL(vprintk_default);
-/*
- * This allows printk to be diverted to another function per cpu.
- * This is useful for calling printk functions from within NMI
- * without worrying about race conditions that can lock up the
- * box.
- */
-DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
-
/**
* printk - print a kernel message
* @fmt: format string
@@ -1838,21 +1841,11 @@ DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
*/
asmlinkage __visible int printk(const char *fmt, ...)
{
- printk_func_t vprintk_func;
va_list args;
int r;
va_start(args, fmt);
-
- /*
- * If a caller overrides the per_cpu printk_func, then it needs
- * to disable preemption when calling printk(). Otherwise
- * the printk_func should be set to the default. No need to
- * disable preemption here.
- */
- vprintk_func = this_cpu_read(printk_func);
r = vprintk_func(fmt, args);
-
va_end(args);
return r;
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 10a1d7dc9313..6eb99c17dbd8 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -13,6 +13,7 @@
#include <linux/ctype.h>
#include <linux/netdevice.h>
#include <linux/kernel.h>
+#include <linux/uuid.h>
#include <linux/slab.h>
#include <linux/compat.h>
@@ -1117,9 +1118,8 @@ static ssize_t bin_uuid(struct file *file,
/* Only supports reads */
if (oldval && oldlen) {
- char buf[40], *str = buf;
- unsigned char uuid[16];
- int i;
+ char buf[UUID_STRING_LEN + 1];
+ uuid_be uuid;
result = kernel_read(file, 0, buf, sizeof(buf) - 1);
if (result < 0)
@@ -1127,24 +1127,15 @@ static ssize_t bin_uuid(struct file *file,
buf[result] = '\0';
- /* Convert the uuid to from a string to binary */
- for (i = 0; i < 16; i++) {
- result = -EIO;
- if (!isxdigit(str[0]) || !isxdigit(str[1]))
- goto out;
-
- uuid[i] = (hex_to_bin(str[0]) << 4) |
- hex_to_bin(str[1]);
- str += 2;
- if (*str == '-')
- str++;
- }
+ result = -EIO;
+ if (uuid_be_to_bin(buf, &uuid))
+ goto out;
if (oldlen > 16)
oldlen = 16;
result = -EFAULT;
- if (copy_to_user(oldval, uuid, oldlen))
+ if (copy_to_user(oldval, &uuid, oldlen))
goto out;
copied = oldlen;