Messages in this thread Patch in this message | | | From | Mauro Carvalho Chehab <> | Subject | [PATCH 09/14] edac: Create a per-Memory Controller bus | Date | Thu, 29 Mar 2012 14:06:56 -0300 |
| |
I'm getting this bug on machines with more than one memory controller:
[ 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 is happening 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.
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com> --- drivers/edac/edac_mc_sysfs.c | 25 +++++++++++++++++++++---- include/linux/edac.h | 1 + 2 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 4ab2e19..319612c 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -357,7 +357,7 @@ static int edac_create_csrow_object(struct mem_ctl_info *mci, return -ENODEV; csrow->dev.type = &csrow_attr_type; - csrow->dev.bus = mci_pdev.bus; + csrow->dev.bus = &mci->bus; device_initialize(&csrow->dev); csrow->dev.parent = &mci->dev; dev_set_name(&csrow->dev, "csrow%d", index); @@ -580,7 +580,7 @@ static int edac_create_dimm_object(struct mem_ctl_info *mci, dimm->mci = mci; dimm->dev.type = &dimm_attr_type; - dimm->dev.bus = mci_pdev.bus; + dimm->dev.bus = &mci->bus; device_initialize(&dimm->dev); dimm->dev.parent = &mci->dev; @@ -937,16 +937,29 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) device_initialize(&mci->dev); mci->dev.parent = &mci_pdev; - mci->dev.bus = mci_pdev.bus; + mci->dev.bus = &mci->bus; dev_set_name(&mci->dev, "mc%d", mci->mc_idx); dev_set_drvdata(&mci->dev, mci); pm_runtime_forbid(&mci->dev); + /* + * The memory controller needs its own bus, in order to avoid + * namespace conflicts at /sys/bus/edac. + */ + debugf0("creating bus %s\n",mci->bus.name); + mci->bus.name = kstrdup(dev_name(&mci->dev), GFP_KERNEL); + err = bus_register(&mci->bus); + if (err < 0) + return err; + debugf0("%s(): creating device %s\n", __func__, dev_name(&mci->dev)); err = device_add(&mci->dev); - if (err < 0) + if (err < 0) { + bus_unregister(&mci->bus); + kfree(mci->bus.name); return err; + } /* * Create the dimm/rank devices @@ -997,6 +1010,8 @@ fail: } put_device(&mci->dev); device_del(&mci->dev); + bus_unregister(&mci->bus); + kfree(mci->bus.name); return err; } @@ -1032,6 +1047,8 @@ void edac_unregister_sysfs(struct mem_ctl_info *mci) debugf1("Unregistering device %s\n", dev_name(&mci->dev)); put_device(&mci->dev); device_del(&mci->dev); + bus_unregister(&mci->bus); + kfree(mci->bus.name); } static void mc_attr_release(struct device *device) diff --git a/include/linux/edac.h b/include/linux/edac.h index 3bfdcb9..0e2cd0b4 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -507,6 +507,7 @@ struct edac_hierarchy { */ struct mem_ctl_info { struct device dev; + struct bus_type bus; struct list_head link; /* for global list of mem_ctl_info structs */ -- 1.7.8 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |