From a2f46ee1ba5ee249ce2ca1ee7a7a0ac46529fb4f Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 16 Mar 2010 08:14:33 +0000 Subject: tipc: fix lockdep warning on address assignment So in the forward porting of various tipc packages, I was constantly getting this lockdep warning everytime I used tipc-config to set a network address for the protocol: [ INFO: possible circular locking dependency detected ] 2.6.33 #1 tipc-config/1326 is trying to acquire lock: (ref_table_lock){+.-...}, at: [] tipc_ref_discard+0x53/0xd4 [tipc] but task is already holding lock: (&(&entry->lock)->rlock#2){+.-...}, at: [] tipc_ref_lock+0x43/0x63 [tipc] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&(&entry->lock)->rlock#2){+.-...}: [] __lock_acquire+0xb67/0xd0f [] lock_acquire+0xdc/0x102 [] _raw_spin_lock_bh+0x3b/0x6e [] tipc_ref_acquire+0xe8/0x11b [tipc] [] tipc_createport_raw+0x78/0x1b9 [tipc] [] tipc_createport+0x8b/0x125 [tipc] [] tipc_subscr_start+0xce/0x126 [tipc] [] process_signal_queue+0x47/0x7d [tipc] [] tasklet_action+0x8c/0xf4 [] __do_softirq+0xf8/0x1cd [] call_softirq+0x1c/0x30 [] _local_bh_enable_ip+0xb8/0xd7 [] local_bh_enable_ip+0xe/0x10 [] _raw_spin_unlock_bh+0x34/0x39 [] spin_unlock_bh.clone.0+0x15/0x17 [tipc] [] tipc_k_signal+0x8d/0xb1 [tipc] [] tipc_core_start+0x8a/0xad [tipc] [] 0xffffffffa01b1087 [] do_one_initcall+0x72/0x18a [] sys_init_module+0xd8/0x23a [] system_call_fastpath+0x16/0x1b -> #0 (ref_table_lock){+.-...}: [] __lock_acquire+0xa11/0xd0f [] lock_acquire+0xdc/0x102 [] _raw_write_lock_bh+0x3b/0x6e [] tipc_ref_discard+0x53/0xd4 [tipc] [] tipc_deleteport+0x40/0x119 [tipc] [] release+0xeb/0x137 [tipc] [] sock_release+0x1f/0x6f [] sock_close+0x27/0x2b [] __fput+0x12a/0x1df [] fput+0x1a/0x1c [] filp_close+0x68/0x72 [] sys_close+0xad/0xe7 [] system_call_fastpath+0x16/0x1b Finally decided I should fix this. Its a straightforward inversion, tipc_ref_acquire takes two locks in this order: ref_table_lock entry->lock while tipc_deleteport takes them in this order: entry->lock (via tipc_port_lock()) ref_table_lock (via tipc_ref_discard()) when the same entry is referenced, we get the above warning. The fix is equally straightforward. Theres no real relation between the entry->lock and the ref_table_lock (they just are needed at the same time), so move the entry->lock aquisition in tipc_ref_acquire down, after we unlock ref_table_lock (this is safe since the ref_table_lock guards changes to the reference table, and we've already claimed a slot there. I've tested the below fix and confirmed that it clears up the lockdep issue Signed-off-by: Neil Horman CC: Allan Stephens Signed-off-by: David S. Miller --- net/tipc/ref.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 414fc34b8bea..8dea66500cf5 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -153,11 +153,11 @@ void tipc_ref_table_stop(void) u32 tipc_ref_acquire(void *object, spinlock_t **lock) { - struct reference *entry; u32 index; u32 index_mask; u32 next_plus_upper; u32 ref; + struct reference *entry = NULL; if (!object) { err("Attempt to acquire reference to non-existent object\n"); @@ -175,30 +175,36 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) index = tipc_ref_table.first_free; entry = &(tipc_ref_table.entries[index]); index_mask = tipc_ref_table.index_mask; - /* take lock in case a previous user of entry still holds it */ - spin_lock_bh(&entry->lock); next_plus_upper = entry->ref; tipc_ref_table.first_free = next_plus_upper & index_mask; ref = (next_plus_upper & ~index_mask) + index; - entry->ref = ref; - entry->object = object; - *lock = &entry->lock; } else if (tipc_ref_table.init_point < tipc_ref_table.capacity) { index = tipc_ref_table.init_point++; entry = &(tipc_ref_table.entries[index]); spin_lock_init(&entry->lock); - spin_lock_bh(&entry->lock); ref = tipc_ref_table.start_mask + index; - entry->ref = ref; - entry->object = object; - *lock = &entry->lock; } else { ref = 0; } write_unlock_bh(&ref_table_lock); + /* + * Grab the lock so no one else can modify this entry + * While we assign its ref value & object pointer + */ + if (entry) { + spin_lock_bh(&entry->lock); + entry->ref = ref; + entry->object = object; + *lock = &entry->lock; + /* + * keep it locked, the caller is responsible + * for unlocking this when they're done with it + */ + } + return ref; } -- cgit v1.2.2 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- net/tipc/core.h | 1 + net/tipc/eth_media.c | 1 + net/tipc/socket.c | 2 +- 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/core.h b/net/tipc/core.h index a881f92a8537..c58a1d16563a 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -56,6 +56,7 @@ #include #include #include +#include #include /* diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 524ba5696d4d..6230d16020c4 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #define MAX_ETH_BEARERS 2 diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 4b235fc1c70f..cfb20b80b3a1 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -40,9 +40,9 @@ #include #include #include -#include #include #include +#include #include #include #include -- cgit v1.2.2