From: Borislav Petkov <bp@suse.de>
Date: Wed, 16 Aug 2017 10:33:44 +0200
Subject: EDAC, ghes: Model a single, logical memory controller
Git-commit: 0fe5f281f749f1d4e462a282ef8ba76407a11fd1
Patch-mainline: v4.15-rc1
References: bsc#1042420
We're enumerating the DIMMs through a DMI walk and since we can't get
any more detailed topological information about which DIMMs belong to
which memory controller, convert it to a single, logical controller
which contains all the DIMMs.
The error reporting path from GHES ghes_edac_report_mem_error() doesn't
get called in NMI context but add a warning about it to catch any
changes in the future as if so, our locking scheme will be insufficient
then.
Signed-off-by: Borislav Petkov <bp@suse.de>
---
drivers/edac/ghes_edac.c | 114 ++++++++++++++++++++---------------------------
1 file changed, 50 insertions(+), 64 deletions(-)
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -30,10 +30,15 @@ struct ghes_edac_pvt {
char msg[80];
};
-static LIST_HEAD(ghes_reglist);
-static DEFINE_MUTEX(ghes_edac_lock);
-static int ghes_edac_mc_num;
+static atomic_t ghes_init = ATOMIC_INIT(0);
+static struct ghes_edac_pvt *ghes_pvt;
+/*
+ * Sync with other, potentially concurrent callers of
+ * ghes_edac_report_mem_error(). We don't know what the
+ * "inventive" firmware would do.
+ */
+static DEFINE_SPINLOCK(ghes_lock);
/* Memory Device - Type 17 of SMBIOS spec */
struct memdev_dmi_entry {
@@ -171,18 +176,26 @@ void ghes_edac_report_mem_error(struct g
enum hw_event_mc_err_type type;
struct edac_raw_error_desc *e;
struct mem_ctl_info *mci;
- struct ghes_edac_pvt *pvt = NULL;
+ struct ghes_edac_pvt *pvt = ghes_pvt;
+ unsigned long flags;
char *p;
u8 grain_bits;
- list_for_each_entry(pvt, &ghes_reglist, list) {
- if (ghes == pvt->ghes)
- break;
- }
if (!pvt) {
pr_err("Internal error: Can't find EDAC structure\n");
return;
}
+
+ /*
+ * We can do the locking below because GHES defers error processing
+ * from NMI to IRQ context. Whenever that changes, we'd at least
+ * know.
+ */
+ if (WARN_ON_ONCE(in_nmi()))
+ return;
+
+ spin_lock_irqsave(&ghes_lock, flags);
+
mci = pvt->mci;
e = &mci->error_desc;
@@ -400,8 +413,8 @@ void ghes_edac_report_mem_error(struct g
(e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
grain_bits, e->syndrome, pvt->detail_location);
- /* Report the error via EDAC API */
edac_raw_mc_handle_error(type, mci, e);
+ spin_unlock_irqrestore(&ghes_lock, flags);
}
int ghes_edac_register(struct ghes *ghes, struct device *dev)
@@ -410,9 +423,14 @@ int ghes_edac_register(struct ghes *ghes
int rc, num_dimm = 0;
struct mem_ctl_info *mci;
struct edac_mc_layer layers[1];
- struct ghes_edac_pvt *pvt;
struct ghes_edac_dimm_fill dimm_fill;
+ /*
+ * We have only one logical memory controller to which all DIMMs belong.
+ */
+ if (atomic_inc_return(&ghes_init) > 1)
+ return 0;
+
/* Get the number of DIMMs */
dmi_walk(ghes_edac_count_dimms, &num_dimm);
@@ -426,26 +444,17 @@ int ghes_edac_register(struct ghes *ghes
layers[0].size = num_dimm;
layers[0].is_virt_csrow = true;
- /*
- * We need to serialize edac_mc_alloc() and edac_mc_add_mc(),
- * to avoid duplicated memory controller numbers
- */
- mutex_lock(&ghes_edac_lock);
- mci = edac_mc_alloc(ghes_edac_mc_num, ARRAY_SIZE(layers), layers,
- sizeof(*pvt));
+ mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct ghes_edac_pvt));
if (!mci) {
pr_info("Can't allocate memory for EDAC data\n");
- mutex_unlock(&ghes_edac_lock);
return -ENOMEM;
}
- pvt = mci->pvt_info;
- memset(pvt, 0, sizeof(*pvt));
- list_add_tail(&pvt->list, &ghes_reglist);
- pvt->ghes = ghes;
- pvt->mci = mci;
- mci->pdev = dev;
+ ghes_pvt = mci->pvt_info;
+ ghes_pvt->ghes = ghes;
+ ghes_pvt->mci = mci;
+ mci->pdev = dev;
mci->mtype_cap = MEM_FLAG_EMPTY;
mci->edac_ctl_cap = EDAC_FLAG_NONE;
mci->edac_cap = EDAC_FLAG_NONE;
@@ -454,36 +463,23 @@ int ghes_edac_register(struct ghes *ghes
mci->ctl_name = "ghes_edac";
mci->dev_name = "ghes";
- if (!ghes_edac_mc_num) {
- if (!fake) {
- pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports.\n");
- pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly.\n");
- pr_info("So, the end result of using this driver varies from vendor to vendor.\n");
- pr_info("If you find incorrect reports, please contact your hardware vendor\n");
- pr_info("to correct its BIOS.\n");
- pr_info("This system has %d DIMM sockets.\n",
- num_dimm);
- } else {
- pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n");
- pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n");
- pr_info("work on such system. Use this driver with caution\n");
- }
+ if (!fake) {
+ pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports.\n");
+ pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly.\n");
+ pr_info("So, the end result of using this driver varies from vendor to vendor.\n");
+ pr_info("If you find incorrect reports, please contact your hardware vendor\n");
+ pr_info("to correct its BIOS.\n");
+ pr_info("This system has %d DIMM sockets.\n", num_dimm);
+ } else {
+ pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n");
+ pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n");
+ pr_info("work on such system. Use this driver with caution\n");
}
if (!fake) {
- /*
- * Fill DIMM info from DMI for the memory controller #0
- *
- * Keep it in blank for the other memory controllers, as
- * there's no reliable way to properly credit each DIMM to
- * the memory controller, as different BIOSes fill the
- * DMI bank location fields on different ways
- */
- if (!ghes_edac_mc_num) {
- dimm_fill.count = 0;
- dimm_fill.mci = mci;
- dmi_walk(ghes_edac_dmidecode, &dimm_fill);
- }
+ dimm_fill.count = 0;
+ dimm_fill.mci = mci;
+ dmi_walk(ghes_edac_dmidecode, &dimm_fill);
} else {
struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
mci->n_layers, 0, 0, 0);
@@ -499,26 +495,16 @@ int ghes_edac_register(struct ghes *ghes
if (rc < 0) {
pr_info("Can't register at EDAC core\n");
edac_mc_free(mci);
- mutex_unlock(&ghes_edac_lock);
return -ENODEV;
}
-
- ghes_edac_mc_num++;
- mutex_unlock(&ghes_edac_lock);
return 0;
}
void ghes_edac_unregister(struct ghes *ghes)
{
struct mem_ctl_info *mci;
- struct ghes_edac_pvt *pvt, *tmp;
- list_for_each_entry_safe(pvt, tmp, &ghes_reglist, list) {
- if (ghes == pvt->ghes) {
- mci = pvt->mci;
- edac_mc_del_mc(mci->pdev);
- edac_mc_free(mci);
- list_del(&pvt->list);
- }
- }
+ mci = ghes_pvt->mci;
+ edac_mc_del_mc(mci->pdev);
+ edac_mc_free(mci);
}