Skip to contentSkip to conversation

BUG: __d_rehash explodes on boot

PATCH Russell King 2 participants 2 messages Jan 14, 2011

lore
Share & tools
lore
#0 lore raw

__d_rehash is dereferencing an almost-NULL pointer on my ARM926. CONFIG_SMP=n and CONFIG_DEBUG_SPINLOCK=y.

The faulting instruction is: strne r3, [r2, #4]
and as can be seen from the register dump below, r2 is 0x00000001, hence the faulting 0x00000005 address.

__d_rehash is essentially:

        spin_lock_bucket(b);
        entry->d_flags &= ~DCACHE_UNHASHED;
        hlist_bl_add_head_rcu(&entry->d_hash, &b->head);
        spin_unlock_bucket(b);

which is:

	bit_spin_lock(0, (unsigned long *)&b->head.first);
        entry->d_flags &= ~DCACHE_UNHASHED;
        hlist_bl_add_head_rcu(&entry->d_hash, &b->head);
	__bit_spin_unlock(0, (unsigned long *)&b->head.first);

bit_spin_lock(0, ptr) sets bit 0 of *ptr, in this case b->head.first if CONFIG_SMP or CONFIG_DEBUG_SPINLOCK is set:

#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
        while (unlikely(test_and_set_bit_lock(bitnum, addr))) {
                while (test_bit(bitnum, addr)) {
                        preempt_enable();
                        cpu_relax();
                        preempt_disable();
                }
        }

#endif

So, b->head.first starts off NULL, and becomes a non-NULL (address 1). hlist_bl_add_head_rcu() does this:

static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n,
struct hlist_bl_head *h)

{
        first = hlist_bl_first(h);
        n->next = first;
        if (first)
                first->pprev = &n->next;

It is the store to first->pprev which is faulting.

hlist_bl_first():

static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) {
return (struct hlist_bl_node *)
((unsigned long)h->first & ~LIST_BL_LOCKMASK);
}

but:
#if defined(CONFIG_SMP)
#define LIST_BL_LOCKMASK 1UL
#else
#define LIST_BL_LOCKMASK 0UL
#endif

So, we have one piece of code which sets bit 0 of addresses, and another bit of code which doesn't clear it before dereferencing the pointer if !CONFIG_SMP && CONFIG_DEBUG_SPINLOCK. With the patch below, I can again sucessfully boot the kernel on my Versatile PB/926 platform.

Kernel messages:
...
Calibrating delay loop... 104.24 BogoMIPS (lpj=521216)
pid_max: default: 32768 minimum: 301
Mount-cache hash table entries: 512
CPU: Testing write buffer coherency: ok
Unhandled fault: alignment exception (0x801) at 0x00000005

Internal error: : 801 [#1]
last sysfs file: 
Modules linked in:
CPU: 0    Not tainted  (2.6.37+ #533)
PC is at __d_rehash+0x74/0xb8
LR is at _d_rehash+0x4c/0x60
pc : [<c00c2bc8>]    lr : [<c00c2c58>]    psr: 20000013

sp : c183fd18 ip : c09cb8c0 fp : c183fd24
r10: c183fdd8 r9 : c183fdec r8 : c183fde4
r7 : c1401940 r6 : c183fe7c r5 : c1401710 r4 : c14016c0 r3 : c14016c8 r2 : 00000001 r1 : 20000013 r0 : c14016c0
Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel
Control: 0005317f Table: 00004000 DAC: 00000017 Process kworker/u:0 (pid: 9, stack limit = 0xc183e270)

Stack: (0xc183fd18 to 0xc1840000)
<trimmed>
Backtrace: 
[<c00c2b54>] (__d_rehash+0x0/0xb8) from [<c00c2c58>] (_d_rehash+0x4c/0x60)
[<c00c2c0c>] (_d_rehash+0x0/0x60) from [<c00c38a0>] (d_rehash+0x24/0x30)
[<c00c387c>] (d_rehash+0x0/0x30) from [<c00d059c>] (simple_lookup+0x44/0x50)
[<c00d0558>] (simple_lookup+0x0/0x50) from [<c00bb03c>] (d_alloc_and_lookup+0x50/0x6c)
[<c00bafec>] (d_alloc_and_lookup+0x0/0x6c) from [<c00bb424>] (do_lookup+0x1b8/0x278)
[<c00bb26c>] (do_lookup+0x0/0x278) from [<c00bcd68>] (link_path_walk+0x210/0xbec)
[<c00bcb58>] (link_path_walk+0x0/0xbec) from [<c00bd958>] (do_path_lookup+0x44/0xd0)
[<c00bd914>] (do_path_lookup+0x0/0xd0) from [<c00be624>] (do_filp_open+0xe4/0x5f8)
[<c00be540>] (do_filp_open+0x0/0x5f8) from [<c00b7b10>] (open_exec+0x2c/0x90)
[<c00b7ae4>] (open_exec+0x0/0x90) from [<c00b8408>] (do_execve+0x88/0x264)
[<c00b8380>] (do_execve+0x0/0x264) from [<c0039254>] (kernel_execve+0x40/0x88)
[<c0039214>] (kernel_execve+0x0/0x88) from [<c005c000>] (____call_usermodehelper+0x88/0x98)
[<c005bf78>] (____call_usermodehelper+0x0/0x98) from [<c004cc90>] (do_exit+0x0/0x5f8)
Code: e59c2000 e3520000 12803008 e5802008 (15823004) 
---[ end trace 1b75b31a2719ed1c ]---
---
 include/linux/list_bl.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)
include/linux/list_bl.h +1 -1
index b2adbb4..5bad17d 100644
@@ -16,7 +16,7 @@
  * some fast and compact auxiliary data.
  */
 
-#if defined(CONFIG_SMP)
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
 #define LIST_BL_LOCKMASK	1UL
 #else
 #define LIST_BL_LOCKMASK	0UL
Signature · 3 lines
Russell King
 Linux kernel    2.6 ARM Linux   - http://www.arm.linux.org.uk/
 maintainer of:
#1 lore raw
Quoted 117 lines · Russell King

__d_rehash is dereferencing an almost-NULL pointer on my ARM926. CONFIG_SMP=n and CONFIG_DEBUG_SPINLOCK=y.

The faulting instruction is:    strne   r3, [r2, #4]
and as can be seen from the register dump below, r2 is 0x00000001, hence the faulting 0x00000005 address.

__d_rehash is essentially:

       spin_lock_bucket(b);
       entry->d_flags &= ~DCACHE_UNHASHED; hlist_bl_add_head_rcu(&entry->d_hash, &b->head); spin_unlock_bucket(b);

which is:

       bit_spin_lock(0, (unsigned long *)&b->head.first); entry->d_flags &= ~DCACHE_UNHASHED; hlist_bl_add_head_rcu(&entry->d_hash, &b->head); __bit_spin_unlock(0, (unsigned long *)&b->head.first);

bit_spin_lock(0, ptr) sets bit 0 of *ptr, in this case b->head.first if CONFIG_SMP or CONFIG_DEBUG_SPINLOCK is set:

#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { while (test_bit(bitnum, addr)) { preempt_enable(); cpu_relax(); preempt_disable();
               }
       }
#endif

So, b->head.first starts off NULL, and becomes a non-NULL (address 1). hlist_bl_add_head_rcu() does this:

static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) {
       first = hlist_bl_first(h);
       n->next = first;
       if (first)
               first->pprev = &n->next;

It is the store to first->pprev which is faulting.

hlist_bl_first():

static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) {
       return (struct hlist_bl_node *)
               ((unsigned long)h->first & ~LIST_BL_LOCKMASK);
}

but:
#if defined(CONFIG_SMP)
#define LIST_BL_LOCKMASK        1UL
#else
#define LIST_BL_LOCKMASK        0UL
#endif

So, we have one piece of code which sets bit 0 of addresses, and another bit of code which doesn't clear it before dereferencing the pointer if !CONFIG_SMP && CONFIG_DEBUG_SPINLOCK.  With the patch below, I can again sucessfully boot the kernel on my Versatile PB/926 platform.

Kernel messages:
...
Calibrating delay loop... 104.24 BogoMIPS (lpj=521216)
pid_max: default: 32768 minimum: 301
Mount-cache hash table entries: 512
CPU: Testing write buffer coherency: ok
Unhandled fault: alignment exception (0x801) at 0x00000005

Internal error: : 801 [#1]
last sysfs file:
Modules linked in:
CPU: 0    Not tainted  (2.6.37+ #533)
PC is at __d_rehash+0x74/0xb8
LR is at _d_rehash+0x4c/0x60
pc : [<c00c2bc8>]    lr : [<c00c2c58>]    psr: 20000013

sp : c183fd18  ip : c09cb8c0  fp : c183fd24
r10: c183fdd8  r9 : c183fdec  r8 : c183fde4
r7 : c1401940  r6 : c183fe7c  r5 : c1401710  r4 : c14016c0 r3 : c14016c8  r2 : 00000001  r1 : 20000013  r0 : c14016c0
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment kernel
Control: 0005317f  Table: 00004000  DAC: 00000017 Process kworker/u:0 (pid: 9, stack limit = 0xc183e270)

Stack: (0xc183fd18 to 0xc1840000)
<trimmed>
Backtrace:
[<c00c2b54>] (__d_rehash+0x0/0xb8) from [<c00c2c58>] (_d_rehash+0x4c/0x60)
[<c00c2c0c>] (_d_rehash+0x0/0x60) from [<c00c38a0>] (d_rehash+0x24/0x30)
[<c00c387c>] (d_rehash+0x0/0x30) from [<c00d059c>] (simple_lookup+0x44/0x50)
[<c00d0558>] (simple_lookup+0x0/0x50) from [<c00bb03c>] (d_alloc_and_lookup+0x50/0x6c)
[<c00bafec>] (d_alloc_and_lookup+0x0/0x6c) from [<c00bb424>] (do_lookup+0x1b8/0x278)
[<c00bb26c>] (do_lookup+0x0/0x278) from [<c00bcd68>] (link_path_walk+0x210/0xbec)
[<c00bcb58>] (link_path_walk+0x0/0xbec) from [<c00bd958>] (do_path_lookup+0x44/0xd0)
[<c00bd914>] (do_path_lookup+0x0/0xd0) from [<c00be624>] (do_filp_open+0xe4/0x5f8)
[<c00be540>] (do_filp_open+0x0/0x5f8) from [<c00b7b10>] (open_exec+0x2c/0x90)
[<c00b7ae4>] (open_exec+0x0/0x90) from [<c00b8408>] (do_execve+0x88/0x264)
[<c00b8380>] (do_execve+0x0/0x264) from [<c0039254>] (kernel_execve+0x40/0x88)
[<c0039214>] (kernel_execve+0x0/0x88) from [<c005c000>] (____call_usermodehelper+0x88/0x98)
[<c005bf78>] (____call_usermodehelper+0x0/0x98) from [<c004cc90>] (do_exit+0x0/0x5f8)
Code: e59c2000 e3520000 12803008 e5802008 (15823004)
---[ end trace 1b75b31a2719ed1c ]---

---
 include/linux/list_bl.h |    2 +-

 1 files changed, 1 insertions(+), 1 deletions(-)
include/linux/list_bl.h +0 -0
index b2adbb4..5bad17d 100644

include/linux/list_bl.h line 22

Quoted 8 lines
include/linux/list_bl.h +1 -1
@@ -16,7 +16,7 @@
  * some fast and compact auxiliary data.
  */
 
-#if defined(CONFIG_SMP)
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
  #define LIST_BL_LOCKMASK       1UL
  #else
  #define LIST_BL_LOCKMASK       0UL

Sigh. Thanks. I guess it is the only thing we can do to keep the UP optimisation...