linux/drivers/edac/edac_module.c

169 lines
3.3 KiB
C
Raw Normal View History

/*
* edac_module.c
*
* (C) 2007 www.softwarebitmaker.com
*
* This file is licensed under the terms of the GNU General Public
* License version 2. This program is licensed "as is" without any
* warranty of any kind, whether express or implied.
*
* Author: Doug Thompson <dougthompson@xmission.com>
*
*/
#include <linux/edac.h>
#include "edac_mc.h"
#include "edac_module.h"
#define EDAC_VERSION "Ver: 3.0.0"
#ifdef CONFIG_EDAC_DEBUG
static int edac_set_debug_level(const char *buf,
const struct kernel_param *kp)
{
unsigned long val;
int ret;
ret = kstrtoul(buf, 0, &val);
if (ret)
return ret;
if (val > 4)
return -EINVAL;
return param_set_int(buf, kp);
}
/* Values of 0 to 4 will generate output */
int edac_debug_level = 2;
EXPORT_SYMBOL_GPL(edac_debug_level);
module_param_call(edac_debug_level, edac_set_debug_level, param_get_int,
&edac_debug_level, 0644);
MODULE_PARM_DESC(edac_debug_level, "EDAC debug level: [0-4], default: 2");
#endif
/*
* edac_op_state_to_string()
*/
char *edac_op_state_to_string(int opstate)
{
if (opstate == OP_RUNNING_POLL)
return "POLLED";
else if (opstate == OP_RUNNING_INTERRUPT)
return "INTERRUPT";
else if (opstate == OP_RUNNING_POLL_INTR)
return "POLL-INTR";
else if (opstate == OP_ALLOC)
return "ALLOC";
else if (opstate == OP_OFFLINE)
return "OFFLINE";
return "UNKNOWN";
}
/*
* sysfs object: /sys/devices/system/edac
* need to export to other files
*/
static struct bus_type edac_subsys = {
.name = "edac",
.dev_name = "edac",
};
static int edac_subsys_init(void)
{
int err;
/* create the /sys/devices/system/edac directory */
err = subsys_system_register(&edac_subsys, NULL);
if (err)
printk(KERN_ERR "Error registering toplevel EDAC sysfs dir\n");
return err;
}
static void edac_subsys_exit(void)
{
bus_unregister(&edac_subsys);
}
/* return pointer to the 'edac' node in sysfs */
struct bus_type *edac_get_sysfs_subsys(void)
{
return &edac_subsys;
}
EXPORT_SYMBOL_GPL(edac_get_sysfs_subsys);
/*
* edac_init
* module initialization entry point
*/
static int __init edac_init(void)
{
int err = 0;
edac_printk(KERN_INFO, EDAC_MC, EDAC_VERSION "\n");
err = edac_subsys_init();
if (err)
return err;
/*
* Harvest and clear any boot/initialization PCI parity errors
*
* FIXME: This only clears errors logged by devices present at time of
* module initialization. We should also do an initial clear
* of each newly hotplugged device.
*/
edac_pci_clear_parity_errors();
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-16 19:41:11 +00:00
err = edac_mc_sysfs_init();
if (err)
goto err_sysfs;
edac_debugfs_init();
err = edac_workqueue_setup();
if (err) {
edac_printk(KERN_ERR, EDAC_MC, "Failure initializing workqueue\n");
goto err_wq;
}
return 0;
err_wq:
edac_debugfs_exit();
edac_mc_sysfs_exit();
err_sysfs:
edac_subsys_exit();
return err;
}
/*
* edac_exit()
* module exit/termination function
*/
static void __exit edac_exit(void)
{
edac_dbg(0, "\n");
/* tear down the various subsystems */
edac_workqueue_teardown();
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-16 19:41:11 +00:00
edac_mc_sysfs_exit();
edac_debugfs_exit();
edac_subsys_exit();
}
/*
* Inform the kernel of our entry and exit points
*/
subsys_initcall(edac_init);
module_exit(edac_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Doug Thompson www.softwarebitmaker.com, et al");
MODULE_DESCRIPTION("Core library routines for EDAC reporting");