提交 7a623c03 编写于 作者: M Mauro Carvalho Chehab

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: NAristeu Rozanski <arozansk@redhat.com>
Cc: Doug Thompson <norsk5@yahoo.com>
Cc: Greg K H <gregkh@linuxfoundation.org>
Signed-off-by: NMauro Carvalho Chehab <mchehab@redhat.com>
上级 b0610bb8
...@@ -218,7 +218,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, ...@@ -218,7 +218,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num,
unsigned size, tot_dimms = 1, count = 1; unsigned size, tot_dimms = 1, count = 1;
unsigned tot_csrows = 1, tot_channels = 1, tot_errcount = 0; unsigned tot_csrows = 1, tot_channels = 1, tot_errcount = 0;
void *pvt, *p, *ptr = NULL; void *pvt, *p, *ptr = NULL;
int i, j, err, row, chn, n, len; int i, j, row, chn, n, len;
bool per_rank = false; bool per_rank = false;
BUG_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0); BUG_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0);
...@@ -374,15 +374,6 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, ...@@ -374,15 +374,6 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num,
mci->op_state = OP_ALLOC; mci->op_state = OP_ALLOC;
INIT_LIST_HEAD(&mci->grp_kobj_list); INIT_LIST_HEAD(&mci->grp_kobj_list);
/*
* Initialize the 'root' kobj for the edac_mc controller
*/
err = edac_mc_register_sysfs_main_kobj(mci);
if (err) {
kfree(mci);
return NULL;
}
/* at this point, the root kobj is valid, and in order to /* at this point, the root kobj is valid, and in order to
* 'free' the object, then the function: * 'free' the object, then the function:
* edac_mc_unregister_sysfs_main_kobj() must be called * edac_mc_unregister_sysfs_main_kobj() must be called
...@@ -403,7 +394,7 @@ void edac_mc_free(struct mem_ctl_info *mci) ...@@ -403,7 +394,7 @@ void edac_mc_free(struct mem_ctl_info *mci)
{ {
debugf1("%s()\n", __func__); debugf1("%s()\n", __func__);
edac_mc_unregister_sysfs_main_kobj(mci); edac_unregister_sysfs(mci);
/* free the mci instance memory here */ /* free the mci instance memory here */
kfree(mci); kfree(mci);
......
此差异已折叠。
...@@ -90,10 +90,7 @@ static int __init edac_init(void) ...@@ -90,10 +90,7 @@ static int __init edac_init(void)
*/ */
edac_pci_clear_parity_errors(); edac_pci_clear_parity_errors();
/* err = edac_mc_sysfs_init();
* now set up the mc_kset under the edac class object
*/
err = edac_sysfs_setup_mc_kset();
if (err) if (err)
goto error; goto error;
...@@ -101,15 +98,11 @@ static int __init edac_init(void) ...@@ -101,15 +98,11 @@ static int __init edac_init(void)
err = edac_workqueue_setup(); err = edac_workqueue_setup();
if (err) { if (err) {
edac_printk(KERN_ERR, EDAC_MC, "init WorkQueue failure\n"); edac_printk(KERN_ERR, EDAC_MC, "init WorkQueue failure\n");
goto workq_fail; goto error;
} }
return 0; return 0;
/* Error teardown stack */
workq_fail:
edac_sysfs_teardown_mc_kset();
error: error:
return err; return err;
} }
...@@ -124,7 +117,7 @@ static void __exit edac_exit(void) ...@@ -124,7 +117,7 @@ static void __exit edac_exit(void)
/* tear down the various subsystems */ /* tear down the various subsystems */
edac_workqueue_teardown(); edac_workqueue_teardown();
edac_sysfs_teardown_mc_kset(); edac_mc_sysfs_exit();
} }
/* /*
......
...@@ -19,12 +19,12 @@ ...@@ -19,12 +19,12 @@
* *
* edac_mc objects * edac_mc objects
*/ */
extern int edac_sysfs_setup_mc_kset(void); /* on edac_mc_sysfs.c */
extern void edac_sysfs_teardown_mc_kset(void); int edac_mc_sysfs_init(void);
extern int edac_mc_register_sysfs_main_kobj(struct mem_ctl_info *mci); void edac_mc_sysfs_exit(void);
extern void edac_mc_unregister_sysfs_main_kobj(struct mem_ctl_info *mci);
extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci); extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci);
extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci); extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci);
void edac_unregister_sysfs(struct mem_ctl_info *mci);
extern int edac_get_log_ue(void); extern int edac_get_log_ue(void);
extern int edac_get_log_ce(void); extern int edac_get_log_ce(void);
extern int edac_get_panic_on_ue(void); extern int edac_get_panic_on_ue(void);
...@@ -34,6 +34,7 @@ extern int edac_mc_get_panic_on_ue(void); ...@@ -34,6 +34,7 @@ extern int edac_mc_get_panic_on_ue(void);
extern int edac_get_poll_msec(void); extern int edac_get_poll_msec(void);
extern int edac_mc_get_poll_msec(void); extern int edac_mc_get_poll_msec(void);
/* on edac_device.c */
extern int edac_device_register_sysfs_main_kobj( extern int edac_device_register_sysfs_main_kobj(
struct edac_device_ctl_info *edac_dev); struct edac_device_ctl_info *edac_dev);
extern void edac_device_unregister_sysfs_main_kobj( extern void edac_device_unregister_sysfs_main_kobj(
......
...@@ -13,6 +13,7 @@ ...@@ -13,6 +13,7 @@
#define _LINUX_EDAC_H_ #define _LINUX_EDAC_H_
#include <linux/atomic.h> #include <linux/atomic.h>
#include <linux/device.h>
#include <linux/kobject.h> #include <linux/kobject.h>
#include <linux/completion.h> #include <linux/completion.h>
#include <linux/workqueue.h> #include <linux/workqueue.h>
...@@ -448,14 +449,15 @@ struct edac_mc_layer { ...@@ -448,14 +449,15 @@ struct edac_mc_layer {
__p; \ __p; \
}) })
/* FIXME: add the proper per-location error counts */
struct dimm_info { struct dimm_info {
struct device dev;
char label[EDAC_MC_LABEL_LEN + 1]; /* DIMM label on motherboard */ char label[EDAC_MC_LABEL_LEN + 1]; /* DIMM label on motherboard */
/* Memory location data */ /* Memory location data */
unsigned location[EDAC_MAX_LAYERS]; unsigned location[EDAC_MAX_LAYERS];
struct kobject kobj; /* sysfs kobject for this csrow */
struct mem_ctl_info *mci; /* the parent */ struct mem_ctl_info *mci; /* the parent */
u32 grain; /* granularity of reported error in bytes */ u32 grain; /* granularity of reported error in bytes */
...@@ -484,6 +486,8 @@ struct dimm_info { ...@@ -484,6 +486,8 @@ struct dimm_info {
* patches in this series will fix this issue. * patches in this series will fix this issue.
*/ */
struct rank_info { struct rank_info {
struct device dev;
int chan_idx; int chan_idx;
struct csrow_info *csrow; struct csrow_info *csrow;
struct dimm_info *dimm; struct dimm_info *dimm;
...@@ -492,6 +496,8 @@ struct rank_info { ...@@ -492,6 +496,8 @@ struct rank_info {
}; };
struct csrow_info { struct csrow_info {
struct device dev;
/* Used only by edac_mc_find_csrow_by_page() */ /* Used only by edac_mc_find_csrow_by_page() */
unsigned long first_page; /* first page number in csrow */ unsigned long first_page; /* first page number in csrow */
unsigned long last_page; /* last page number in csrow */ unsigned long last_page; /* last page number in csrow */
...@@ -517,15 +523,6 @@ struct mcidev_sysfs_group { ...@@ -517,15 +523,6 @@ struct mcidev_sysfs_group {
const struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */ const struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */
}; };
struct mcidev_sysfs_group_kobj {
struct list_head list; /* list for all instances within a mc */
struct kobject kobj; /* kobj for the group */
const struct mcidev_sysfs_group *grp; /* group description table */
struct mem_ctl_info *mci; /* the parent */
};
/* mcidev_sysfs_attribute structure /* mcidev_sysfs_attribute structure
* used for driver sysfs attributes and in mem_ctl_info * used for driver sysfs attributes and in mem_ctl_info
* sysfs top level entries * sysfs top level entries
...@@ -536,13 +533,27 @@ struct mcidev_sysfs_attribute { ...@@ -536,13 +533,27 @@ struct mcidev_sysfs_attribute {
const struct mcidev_sysfs_group *grp; /* Points to a group of attributes */ const struct mcidev_sysfs_group *grp; /* Points to a group of attributes */
/* Ops for show/store values at the attribute - not used on group */ /* Ops for show/store values at the attribute - not used on group */
ssize_t (*show)(struct mem_ctl_info *,char *); ssize_t (*show)(struct mem_ctl_info *, char *);
ssize_t (*store)(struct mem_ctl_info *, const char *,size_t); ssize_t (*store)(struct mem_ctl_info *, const char *, size_t);
void *priv;
};
/*
* struct errcount_attribute - used to store the several error counts
*/
struct errcount_attribute_data {
int n_layers;
int pos[EDAC_MAX_LAYERS];
int layer0, layer1, layer2;
}; };
/* MEMORY controller information structure /* MEMORY controller information structure
*/ */
struct mem_ctl_info { struct mem_ctl_info {
struct device dev;
struct bus_type bus;
struct list_head link; /* for global list of mem_ctl_info structs */ struct list_head link; /* for global list of mem_ctl_info structs */
struct module *owner; /* Module owner of this control struct */ struct module *owner; /* Module owner of this control struct */
...@@ -587,7 +598,15 @@ struct mem_ctl_info { ...@@ -587,7 +598,15 @@ struct mem_ctl_info {
struct csrow_info *csrows; struct csrow_info *csrows;
unsigned nr_csrows, num_cschannel; unsigned nr_csrows, num_cschannel;
/* Memory Controller hierarchy */ /*
* Memory Controller hierarchy
*
* There are basically two types of memory controller: the ones that
* sees memory sticks ("dimms"), and the ones that sees memory ranks.
* All old memory controllers enumerate memories per rank, but most
* of the recent drivers enumerate memories per DIMM, instead.
* When the memory controller is per rank, mem_is_per_rank is true.
*/
unsigned n_layers; unsigned n_layers;
struct edac_mc_layer *layers; struct edac_mc_layer *layers;
bool mem_is_per_rank; bool mem_is_per_rank;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册