aboutsummaryrefslogtreecommitdiff
path: root/drivers/edac
diff options
context:
space:
mode:
authorMauro Carvalho Chehab <mchehab@redhat.com>2012-10-31 10:42:29 -0300
committerMauro Carvalho Chehab <mchehab@redhat.com>2013-02-21 11:06:38 -0300
commit80cc7d87d5eb34375f916d282450a0906a8ead60 (patch)
treebcdec36f2945da29b13955d821d5a786f1f78139 /drivers/edac
parentc2c93dbc97622e26dc19edc71e50ebaa996d7804 (diff)
edac: lock module owner to avoid error report conflicts
APEI GHES and i7core_edac/sb_edac currently can be loaded at the same time, but those are Highlander modules: "There can be only one". There are two reasons for that: 1) Each driver assumes that it is the only one registering at the EDAC core, as it is driver's responsibility to number the memory controllers, and all of them start from 0; 2) If BIOS is handling the memory errors, the OS can't also be doing it, as one will mangle with the other. So, we need to add an module owner's lock at the EDAC core, in order to avoid having two different modules handling memory errors at the same time. The best way for doing this lock seems to use the driver's name, as this is unique, and won't require changes on every driver. Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Diffstat (limited to 'drivers/edac')
-rw-r--r--drivers/edac/edac_mc.c25
1 files changed, 21 insertions, 4 deletions
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 78d8c7d6e76..34eb9703ed3 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -42,6 +42,12 @@
static DEFINE_MUTEX(mem_ctls_mutex);
static LIST_HEAD(mc_devices);
+/*
+ * Used to lock EDAC MC to just one module, avoiding two drivers e. g.
+ * apei/ghes and i7core_edac to be used at the same time.
+ */
+static void const *edac_mc_owner;
+
unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
unsigned len)
{
@@ -659,9 +665,9 @@ fail1:
return 1;
}
-static void del_mc_from_global_list(struct mem_ctl_info *mci)
+static int del_mc_from_global_list(struct mem_ctl_info *mci)
{
- atomic_dec(&edac_handlers);
+ int handlers = atomic_dec_return(&edac_handlers);
list_del_rcu(&mci->link);
/* these are for safe removal of devices from global list while
@@ -669,6 +675,8 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci)
*/
synchronize_rcu();
INIT_LIST_HEAD(&mci->link);
+
+ return handlers;
}
/**
@@ -712,6 +720,7 @@ EXPORT_SYMBOL(edac_mc_find);
/* FIXME - should a warning be printed if no error detection? correction? */
int edac_mc_add_mc(struct mem_ctl_info *mci)
{
+ int ret = -EINVAL;
edac_dbg(0, "\n");
#ifdef CONFIG_EDAC_DEBUG
@@ -742,6 +751,11 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
#endif
mutex_lock(&mem_ctls_mutex);
+ if (edac_mc_owner && edac_mc_owner != mci->mod_name) {
+ ret = -EPERM;
+ goto fail0;
+ }
+
if (add_mc_to_global_list(mci))
goto fail0;
@@ -768,6 +782,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
edac_mc_printk(mci, KERN_INFO, "Giving out device to '%s' '%s':"
" DEV %s\n", mci->mod_name, mci->ctl_name, edac_dev_name(mci));
+ edac_mc_owner = mci->mod_name;
+
mutex_unlock(&mem_ctls_mutex);
return 0;
@@ -776,7 +792,7 @@ fail1:
fail0:
mutex_unlock(&mem_ctls_mutex);
- return 1;
+ return ret;
}
EXPORT_SYMBOL_GPL(edac_mc_add_mc);
@@ -802,7 +818,8 @@ struct mem_ctl_info *edac_mc_del_mc(struct device *dev)
return NULL;
}
- del_mc_from_global_list(mci);
+ if (!del_mc_from_global_list(mci))
+ edac_mc_owner = NULL;
mutex_unlock(&mem_ctls_mutex);
/* flush workq processes */