The recent rework of probe_kernel_address() and its conversion to
get_kernel_nofault() inadvertently broke is_prefetch(). Before this change,
probe_kernel_address() was used as a sloppy "read user or kernel memory"
helper, but it doesn't do that any more. The new get_kernel_nofault()
reads *kernel* memory only, which completely broke is_prefetch() for user
access.
Adjust the code to the the correct accessor based on access mode. The
manual address bounds check is no longer necessary, since the accessor
helpers (get_user() / get_kernel_nofault()) do the right thing all by
themselves. As a bonus, by using the correct accessor, we don't need the
open-coded address bounds check.
Fixes: eab0c6089b68 ("maccess: unify the probe kernel arch hooks")
Cc: stable(a)vger.kernel.org
Cc: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Christoph Hellwig <hch(a)lst.de>
Cc: Alexei Starovoitov <ast(a)kernel.org>
Cc: Daniel Borkmann <daniel(a)iogearbox.net>
Cc: Masami Hiramatsu <mhiramat(a)kernel.org>
Signed-off-by: Andy Lutomirski <luto(a)kernel.org>
---
arch/x86/mm/fault.c | 27 +++++++++++++++++----------
1 file changed, 17 insertions(+), 10 deletions(-)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f1f1b5a0956a..441c3e9b8971 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -54,7 +54,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
* 32-bit mode:
*
* Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
- * Check that here and ignore it.
+ * Check that here and ignore it. This is AMD erratum #91.
*
* 64-bit mode:
*
@@ -83,11 +83,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
#ifdef CONFIG_X86_64
case 0x40:
/*
- * In AMD64 long mode 0x40..0x4F are valid REX prefixes
- * Need to figure out under what instruction mode the
- * instruction was issued. Could check the LDT for lm,
- * but for now it's good enough to assume that long
- * mode only uses well known segments or kernel.
+ * In 64-bit mode 0x40..0x4F are valid REX prefixes
*/
return (!user_mode(regs) || user_64bit_mode(regs));
#endif
@@ -127,20 +123,31 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
instr = (void *)convert_ip_to_linear(current, regs);
max_instr = instr + 15;
- if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE_MAX)
- return 0;
+ /*
+ * This code has historically always bailed out if IP points to a
+ * not-present page (e.g. due to a race). No one has ever
+ * complained about this.
+ */
+ pagefault_disable();
while (instr < max_instr) {
unsigned char opcode;
- if (get_kernel_nofault(opcode, instr))
- break;
+ if (user_mode(regs)) {
+ if (get_user(opcode, instr))
+ break;
+ } else {
+ if (get_kernel_nofault(opcode, instr))
+ break;
+ }
instr++;
if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
break;
}
+
+ pagefault_enable();
return prefetch;
}
--
2.29.2
printk_safe_flush_on_panic() caused the following deadlock on our
server:
CPU0: CPU1:
panic rcu_dump_cpu_stacks
kdump_nmi_shootdown_cpus nmi_trigger_cpumask_backtrace
register_nmi_handler(crash_nmi_callback) printk_safe_flush
__printk_safe_flush
raw_spin_lock_irqsave(&read_lock)
// send NMI to other processors
apic_send_IPI_allbutself(NMI_VECTOR)
// NMI interrupt, dead loop
crash_nmi_callback
printk_safe_flush_on_panic
printk_safe_flush
__printk_safe_flush
// deadlock
raw_spin_lock_irqsave(&read_lock)
DEADLOCK: read_lock is taken on CPU1 and will never get released.
It happens when panic() stops a CPU by NMI while it has been in
the middle of printk_safe_flush().
Handle the lock the same way as logbuf_lock. The printk_safe buffers
are flushed only when both locks can be safely taken. It can avoid
the deadlock _in this particular case_ at expense of losing contents
of printk_safe buffers.
Note: It would actually be safe to re-init the locks when all CPUs were
stopped by NMI. But it would require passing this information
from arch-specific code. It is not worth the complexity.
Especially because logbuf_lock and printk_safe buffers have been
obsoleted by the lockless ring buffer.
Fixes: cf9b1106c81c ("printk/nmi: flush NMI messages on the system panic")
Signed-off-by: Muchun Song <songmuchun(a)bytedance.com>
Reviewed-by: Petr Mladek <pmladek(a)suse.com>
Cc: <stable(a)vger.kernel.org>
---
kernel/printk/printk_safe.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index a0e6f746de6c..2e9e3ed7d63e 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -45,6 +45,8 @@ struct printk_safe_seq_buf {
static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq);
static DEFINE_PER_CPU(int, printk_context);
+static DEFINE_RAW_SPINLOCK(safe_read_lock);
+
#ifdef CONFIG_PRINTK_NMI
static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq);
#endif
@@ -180,8 +182,6 @@ static void report_message_lost(struct printk_safe_seq_buf *s)
*/
static void __printk_safe_flush(struct irq_work *work)
{
- static raw_spinlock_t read_lock =
- __RAW_SPIN_LOCK_INITIALIZER(read_lock);
struct printk_safe_seq_buf *s =
container_of(work, struct printk_safe_seq_buf, work);
unsigned long flags;
@@ -195,7 +195,7 @@ static void __printk_safe_flush(struct irq_work *work)
* different CPUs. This is especially important when printing
* a backtrace.
*/
- raw_spin_lock_irqsave(&read_lock, flags);
+ raw_spin_lock_irqsave(&safe_read_lock, flags);
i = 0;
more:
@@ -232,7 +232,7 @@ static void __printk_safe_flush(struct irq_work *work)
out:
report_message_lost(s);
- raw_spin_unlock_irqrestore(&read_lock, flags);
+ raw_spin_unlock_irqrestore(&safe_read_lock, flags);
}
/**
@@ -278,6 +278,14 @@ void printk_safe_flush_on_panic(void)
raw_spin_lock_init(&logbuf_lock);
}
+ if (raw_spin_is_locked(&safe_read_lock)) {
+ if (num_online_cpus() > 1)
+ return;
+
+ debug_locks_off();
+ raw_spin_lock_init(&safe_read_lock);
+ }
+
printk_safe_flush();
}
--
2.11.0