mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 03:09:34 +03:00
e811949a57
It turns out that the previous rwlock implementation worked well but did not integrate properly with the upstream kernel lock profiling/ analysis tools. This is a major problem since it would be awfully nice to be able to use the automatic lock checker and profiler. The problem is that the upstream lock tools use the pre-processor to create a lock class for each uniquely named locked. Since the rwsem was embedded in a wrapper structure the name was always the same. The effect was that we only ended up with one lock class for the entire SPL which caused the lock dependency checker to flag nearly everything as a possible deadlock. The solution was to directly map a krwlock to a Linux rwsem using a typedef there by eliminating the wrapper structure. This was not done initially because the rwsem implementation is specific to the arch. To fully implement the Solaris krwlock API using only the provided rwsem API is not possible. It can only be done by directly accessing some of the internal data member of the rwsem structure. For example, the Linux API provides a different function for dropping a reader vs writer lock. Whereas the Solaris API uses the same function and the caller does not pass in what type of lock it is. This means to properly drop the lock we need to determine if the lock is currently a reader or writer lock. Then we need to call the proper Linux API function. Unfortunately, there is no provided API for this so we must extracted this information directly from arch specific lock implementation. This is all do able, and what I did, but it does complicate things considerably. The good news is that in addition to the profiling benefits of this change. We may see performance improvements due to slightly reduced overhead when creating rwlocks and manipulating them. The only function I was forced to sacrafice was rw_owner() because this information is simply not stored anywhere in the rwsem. Luckily this appears not to be a commonly used function on Solaris, and it is my understanding it is mainly used for debugging anyway. In addition to the core rwlock changes, extensive updates were made to the rwlock regression tests. Each class of test was extended to provide more API coverage and to be more rigerous in checking for misbehavior. This is a pretty significant change and with that in mind I have been careful to validate it on several platforms before committing. The full SPLAT regression test suite was run numberous times on all of the following platforms. This includes various kernels ranging from 2.6.16 to 2.6.29. - SLES10 (ppc64) - SLES11 (x86_64) - CHAOS4.2 (x86_64) - RHEL5.3 (x86_64) - RHEL6 (x86_64) - FC11 (x86_64)
107 lines
3.3 KiB
Diff
107 lines
3.3 KiB
Diff
Required missing symbols for FC11 kernels (2.6.29.4-167.fc11.x86_64)
|
|
|
|
* get_vmalloc_info()
|
|
There is no clean API in the kernel for modules to check the virtual
|
|
memory state of the system. This information is available in user
|
|
space under /proc/meminfo and the details for every virtual memory
|
|
node are available under /proc/vmallocinfo.
|
|
|
|
* groups_search()
|
|
This support is easily replicated if the symbol is not provided by the
|
|
kernel. However exporting the symbol from the kernel is preferable.
|
|
This is required by the solaris credential API.
|
|
|
|
* task_curr()
|
|
This symbol is used by the solaris adaptive mutex implementation. If
|
|
unavailable then all solaris mutexs behave strictly like linux style
|
|
semaphones. If available then the mutex may spin for a short while,
|
|
rather than sleep, if the holder of the lock is currently executing.
|
|
|
|
* first_online_pgdat()
|
|
* next_online_pgdat()
|
|
* next_zone()
|
|
Required helper functions for the zone iterators for_each_zone() and
|
|
for_each_populated_zone(). These symbols were previously available
|
|
in 2.6.17 kernels, marked unused in 2.6.18 kernels, and removed as
|
|
of the 2.6.19 kernel series. The information is available in user
|
|
space under /proc/zoneinfo.
|
|
|
|
diff --git a/fs/proc/mmu.c b/fs/proc/mmu.c
|
|
index 8ae221d..081c7b5 100644
|
|
--- a/fs/proc/mmu.c
|
|
+++ b/fs/proc/mmu.c
|
|
@@ -58,3 +58,4 @@ void get_vmalloc_info(struct vmalloc_info *vmi)
|
|
read_unlock(&vmlist_lock);
|
|
}
|
|
}
|
|
+EXPORT_SYMBOL(get_vmalloc_info);
|
|
diff --git a/kernel/groups.c b/kernel/groups.c
|
|
index 2b45b2e..24b62f8 100644
|
|
--- a/kernel/groups.c
|
|
+++ b/kernel/groups.c
|
|
@@ -153,6 +153,7 @@ int groups_search(const struct group_info *group_info, gid_t grp)
|
|
}
|
|
return 0;
|
|
}
|
|
+EXPORT_SYMBOL(groups_search);
|
|
|
|
/**
|
|
* set_groups - Change a group subscription in a set of credentials
|
|
diff --git a/kernel/sched.c b/kernel/sched.c
|
|
index 1b59e26..8728c52 100644
|
|
--- a/kernel/sched.c
|
|
+++ b/kernel/sched.c
|
|
@@ -1883,10 +1883,11 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
|
|
* task_curr - is this task currently executing on a CPU?
|
|
* @p: the task in question.
|
|
*/
|
|
-inline int task_curr(const struct task_struct *p)
|
|
+task_curr(const struct task_struct *p)
|
|
{
|
|
return cpu_curr(task_cpu(p)) == p;
|
|
}
|
|
+EXPORT_SYMBOL(task_curr);
|
|
|
|
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
|
|
{
|
|
diff --git a/mm/mmzone.c b/mm/mmzone.c
|
|
index f5b7d17..1468a22 100644
|
|
--- a/mm/mmzone.c
|
|
+++ b/mm/mmzone.c
|
|
@@ -14,6 +14,7 @@ struct pglist_data *first_online_pgdat(void)
|
|
{
|
|
return NODE_DATA(first_online_node);
|
|
}
|
|
+EXPORT_SYMBOL(first_online_pgdat);
|
|
|
|
struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
|
|
{
|
|
@@ -23,6 +24,7 @@ struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
|
|
return NULL;
|
|
return NODE_DATA(nid);
|
|
}
|
|
+EXPORT_SYMBOL(next_online_pgdat);
|
|
|
|
/*
|
|
* next_zone - helper magic for for_each_zone()
|
|
@@ -42,6 +44,7 @@ struct zone *next_zone(struct zone *zone)
|
|
}
|
|
return zone;
|
|
}
|
|
+EXPORT_SYMBOL(next_zone);
|
|
|
|
static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
|
|
{
|
|
diff --git a/kernel/fork.c b/kernel/fork.c
|
|
index 9b42695..852499e 100644
|
|
--- a/kernel/fork.c
|
|
+++ b/kernel/fork.c
|
|
@@ -159,6 +159,7 @@ void __put_task_struct(struct task_struct *tsk)
|
|
if (!profile_handoff_task(tsk))
|
|
free_task(tsk);
|
|
}
|
|
+EXPORT_SYMBOL(__put_task_struct);
|
|
|
|
/*
|
|
* macro override instead of weak attribute alias, to workaround
|